© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196000
    Prev
    Next
    INDEX
    Explanations

    tomato paste

    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
     was
    1.14
    '
    1.01
    erde
    0.93
    weise
    0.89
     that
    0.86
     que
    0.84
     الك
    0.83
     be
    0.82
     como
    0.81
     beneficio
    0.79
    POSITIVE LOGITS
    i
    1.22
    و
    1.16
    the
    1.14
    in
    1.02
    ın
    0.97
    ي
    0.93
    se
    0.89
    u
    0.87
    as
    0.87
    ре
    0.86
    Activations Density 0.000%

    No Known Activations