© 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. 122828
    Prev
    Next
    INDEX
    Explanations

    zefir, spectrum, zahir, al-zahara

    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
    '
    0.73
    我们
    0.72
     irá
    0.71
    ’
    0.69
     fez
    0.68
     arka
    0.66
             
    0.66
     pv
    0.64
     ks
    0.64
     oti
    0.63
    POSITIVE LOGITS
    ла
    0.92
    се
    0.77
    ?
    0.74
    !
    0.69
    ры
    0.68
    the
    0.66
    மாக
    0.66
    ية
    0.66
    ール
    0.66
    ல்
    0.63
    Activations Density 0.000%

    No Known Activations