© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32142
    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_7_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
    <0x0D>
    1.02
    </h2>
    0.82
    <0x0C>
    0.75
    '=
    0.74
    евич
    0.73
    Although
    0.72
    }$;
    0.70
    Both
    0.68
    <h2>
    0.68
     הם
    0.68
    POSITIVE LOGITS
    t
    1.70
    x
    1.13
    ra
    1.12
    g
    0.96
    ラ
    0.96
    d
    0.95
    S
    0.95
    c
    0.92
    ne
    0.92
    り
    0.91
    Activations Density 0.000%

    No Known Activations