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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8404
    Prev
    Next
    INDEX
    Explanations

    code, specifically "._" followed by code-related words

    oai_token-act-pair · gemini-2.0-flash

    ._

    np_max-act · gemini-2.0-flash

    ._ Method used: 1

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.50
     Monfieur
    -1.41
     itſelf
    -1.32
     Anſ
    -1.31
     Reſ
    -1.30
     Majefty
    -1.30
     Theſe
    -1.30
     Houſe
    -1.26
     ſche
    -1.23
     Verſ
    -1.20
    POSITIVE LOGITS
     a
    0.89
     an
    0.82
     it
    0.79
     to
    0.76
     in
    0.74
     we
    0.69
     for
    0.68
    quehanna
    0.65
     as
    0.65
     is
    0.65
    Activations Density 3.385%

    No Known Activations