© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59236
    Prev
    Next
    INDEX
    Explanations

    perches on

    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_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
    u
    1.93
    i
    1.66
    the
    1.61
    و
    1.58
    ح
    1.46
    ו
    1.46
    a
    1.45
    of
    1.45
    by
    1.42
    at
    1.32
    POSITIVE LOGITS
    ’
    1.13
    ский
    1.02
    다는
    0.96
    ’।
    0.89
    仡
    0.89
     suelo
    0.87
     perch
    0.84
     cultured
    0.84
    다면
    0.82
    ,
    0.82
    Activations Density 0.000%

    No Known Activations