© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 69
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cellSize
    1.47
    ್
    1.46
     tokenize
    1.43
    damn
    1.38
    dropout
    1.32
     kinds
    1.32
     pageSize
    1.32
    $}
    1.30
     forth
    1.30
    ्यूम
    1.29
    POSITIVE LOGITS
    に
    1.53
    로
    1.44
    то
    1.36
    is
    1.31
    ী
    1.24
    <0xF4>
    1.24
    ات
    1.23
    á
    1.22
     muestra
    1.21
    aser
    1.20
    Activations Density 0.007%

    No Known Activations