© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122584
    Prev
    Next
    INDEX
    Explanations

    *ind* or *find* followed by space/punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    >
    0.86
    ↵
    0.75
     categor
    0.68
     αλλά
    0.68
    ﺎ
    0.68
    -
    0.68
    O
    0.64
    /
    0.63
    <
    0.59
     για
    0.59
    POSITIVE LOGITS
    на
    0.89
    ب
    0.84
    on
    0.82
    و
    0.79
    ام
    0.78
    in
    0.77
    ال
    0.75
    ص
    0.75
    ی
    0.73
    ne
    0.71
    Activations Density 0.000%

    No Known Activations