Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14613
    Prev
    Next
    INDEX
    Explanations

    dates including months and days

    oai_token-act-pair · gemini-2.0-flash

    say "month or holiday"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RTLI
    -0.53
     تانيه
    -0.52
     bint
    -0.52
     swears
    -0.50
    IntoConstraints
    -0.50
    cektir
    -0.50
     OnInit
    -0.49
     swear
    -0.49
     Gor
    -0.48
    ScopeManager
    -0.47
    POSITIVE LOGITS
     Black
    0.94
    Black
    0.86
     BLACK
    0.74
    BLACK
    0.69
     black
    0.67
    ItemBackground
    0.63
    black
    0.63
    QMetaType
    0.59
    sizeCache
    0.59
     Blacks
    0.59
    Activations Density 2.011%

    No Known Activations