© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2998
    Prev
    Next
    INDEX
    Explanations

    references to legal code and statutes.

    oai_token-act-pair · gemini-2.0-flash

    say "number 8"

    np_max-act-logits · gemini-2.0-flash

    say "8" Method used: 2 — because every token after the max-activating token is 8 — say "8"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109

    say "8" Method used: 2 — because tokens after the maxima are all the digit 8 — say "8"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.77
     snippetHide
    -0.70
     Six
    -0.69
     nineteen
    -0.68
     six
    -0.67
     seventeenth
    -0.67
    StoreMessageInfo
    -0.66
     sixth
    -0.65
    TypedDataSet
    -0.65
     kaynağından
    -0.64
    POSITIVE LOGITS
    8
    0.88
     eig
    0.54
    ８
    0.48
    ۸
    0.46
     ۸
    0.45
     an
    0.45
     eight
    0.45
    ochet
    0.44
    ibut
    0.44
    емое
    0.44
    Activations Density 3.081%

    No Known Activations