© 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. 328
    Prev
    Next
    INDEX
    Explanations

    references to incarceration and/or punishment, plus the word "you".

    oai_token-act-pair · gemini-2.0-flash

    say "Mis" words

    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
    ///</
    -0.62
    jsonwebtoken
    -0.62
    bited
    -0.50
    WireFormatLite
    -0.50
    vantaged
    -0.49
    зопас
    -0.47
     محفوظة
    -0.47
    ჟ
    -0.47
    ╝
    -0.46
     compliance
    -0.45
    POSITIVE LOGITS
     mis
    1.48
    Mis
    1.09
     Mis
    1.07
    mis
    0.97
     MIS
    0.85
    ValueStyle
    0.71
     mise
    0.63
    BeginContext
    0.62
    MIS
    0.59
     GenerationType
    0.57
    Activations Density 4.633%

    No Known Activations