© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40871
    Prev
    Next
    INDEX
    Explanations

    fraud and abuse

    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
    ك
    0.73
    ur
    0.70
    ли
    0.66
    一样的
    0.62
    ре
    0.61
    vá
    0.60
    öld
    0.60
    ො
    0.60
    يش
    0.58
     Biographical
    0.58
    POSITIVE LOGITS
    ی
    0.75
    s
    0.71
    ༡
    0.65
     and
    0.65
    {
    0.64
    did
    0.63
    sset
    0.62
    یز
    0.61
    ༤
    0.61
    댜
    0.61
    Activations Density 0.005%

    No Known Activations