© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9224
    Prev
    Next
    INDEX
    Explanations

    strings of digits separated by hyphens, often appearing in the context of scientific publications or mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    say "5"

    np_max-act-logits · gemini-2.0-flash
    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
     Efq
    -0.81
     aught
    -0.75
     Theſe
    -0.71
     Jefus
    -0.68
     myſelf
    -0.66
     itſelf
    -0.65
     himſelf
    -0.63
     raiſ
    -0.63
     ſhe
    -0.60
     becauſe
    -0.60
    POSITIVE LOGITS
    SequentialGroup
    0.82
    WebElementEntity
    0.80
    5
    0.70
    SourceChecksum
    0.57
    fjspx
    0.57
    jgl
    0.56
     estekak
    0.55
    DebuggerNonUser
    0.55
     otomatig
    0.55
    Filmografie
    0.53
    Activations Density 11.555%

    No Known Activations