© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193169
    Prev
    Next
    INDEX
    Explanations

    tokens following "iw"

    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_4_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
    -
    0.76
    \
    0.73
    عة
    0.73
    عت
    0.71
    νες
    0.68
     didn
    0.68
    didn
    0.68
    ão
    0.67
     Favre
    0.66
    ón
    0.63
    POSITIVE LOGITS
    其他
    1.02
    on
    0.91
    να
    0.89
    ח
    0.87
    ו
    0.81
    お
    0.80
    ко
    0.77
    り
    0.76
    во
    0.73
    ப
    0.72
    Activations Density 0.003%

    No Known Activations