© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6151
    Prev
    Next
    INDEX
    Explanations

    words related to the act of discussing or sharing information

    oai_token-act-pair · gemini-2.0-flash

    words related to discussion and dialogue

    np_token-act-pair-logits · gpt-4o-mini

    discussing, examining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    for
    -0.49
    with
    -0.46
    or
    -0.46
     continúas
    -0.45
    up
    -0.45
    p
    -0.44
    they
    -0.44
    pl
    -0.44
     сравнению
    -0.44
    from
    -0.43
    POSITIVE LOGITS
     how
    1.23
    MigrationBuilder
    0.87
     cómo
    0.81
     ways
    0.79
     why
    0.79
     HOW
    0.75
     कैसे
    0.75
    how
    0.74
    __':
    0.74
    GraphicsUnit
    0.73
    Activations Density 3.840%

    No Known Activations