© 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. 34841
    Prev
    Next
    INDEX
    Explanations

    final part of words, suffixes

    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
    ุ
    0.78
    ية
    0.76
    мена
    0.75
    ↵↵
    0.72
    ین
    0.72
     b
    0.68
    ת
    0.66
    する
    0.65
    ط
    0.65
     ine
    0.64
    POSITIVE LOGITS
    et
    0.84
    ,
    0.79
    Cel
    0.77
    ag
    0.73
    ->
    0.72
    Calc
    0.71
    l
    0.69
    hah
    0.68
    Und
    0.68
    bella
    0.68
    Activations Density 0.008%

    No Known Activations