© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124858
    Prev
    Next
    INDEX
    Explanations

    pizza box

    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
    тың
    0.60
     ailment
    0.58
     experiments
    0.58
    ມັນ
    0.58
    .
    0.57
     emerging
    0.54
    '
    0.54
    iel
    0.53
     masyarakat
    0.52
     It
    0.52
    POSITIVE LOGITS
    an
    0.83
    in
    0.79
    i
    0.77
    was
    0.75
    ي
    0.71
    ו
    0.70
    a
    0.70
    ки
    0.69
    on
    0.68
    at
    0.68
    Activations Density 0.001%

    No Known Activations