© 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. 43801
    Prev
    Next
    INDEX
    Explanations

    misfire or misconduct

    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
    os
    0.94
    ar
    0.79
    ang
    0.79
    y
    0.79
    ight
    0.79
    as
    0.76
    em
    0.75
    en
    0.75
    ed
    0.71
    es
    0.71
    POSITIVE LOGITS
    la
    0.78
     п
    0.66
     can
    0.66
    $
    0.65
    \
    0.64
    lt
    0.63
     maniac
    0.59
     ב
    0.58
    $;
    0.58
    </b>
    0.56
    Activations Density 0.002%

    No Known Activations