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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60218
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_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
    '
    1.23
    ーカー
    1.04
     процессо
    1.02
    ーパー
    1.01
    朤
    0.97
    <0x89>
    0.95
    こだわり
    0.94
     роках
    0.93
     клуба
    0.93
     мнение
    0.91
    POSITIVE LOGITS
    g
    1.42
    b
    1.29
    d
    1.25
    k
    1.14
    ar
    1.05
    ला
    1.05
     from
    1.04
    ur
    1.03
    ك
    1.02
     at
    1.02
    Activations Density 0.000%

    No Known Activations