© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8087
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    oai_token-act-pair · gemini-2.0-flash

    data and numbers

    np_max-act-logits · gemini-2.0-flash

    say "numbers" Method used: 2 — tokens after are numeric, so say "numbers"

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    6
    -1.15
     sixth
    -1.09
     fifth
    -1.07
    5
    -1.07
    6
    -0.99
    7
    -0.98
     seventh
    -0.95
    5
    -0.93
     six
    -0.91
     fün
    -0.88
    POSITIVE LOGITS
    0
    0.59
    PageContext
    0.57
    ⓘ
    0.54
    Gemeinden
    0.53
    igshid
    0.51
    ,‎
    0.49
     jspb
    0.47
     Moraes
    0.47
    DataBind
    0.47
     rêver
    0.47
    Activations Density 15.603%

    No Known Activations