© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85276
    Prev
    Next
    INDEX
    Explanations

    harm to victims and property owners

    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_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    apak
    0.47
    uk
    0.44
    uant
    0.42
    fer
    0.41
    orm
    0.40
    ammens
    0.40
    fo
    0.39
    ';
    0.39
    pe
    0.38
    ng
    0.38
    POSITIVE LOGITS
     elusive
    0.43
    ؒ
    0.41
    தும்
    0.39
    Trust
    0.38
     تشدد
    0.38
    Ⴀ
    0.38
     overweight
    0.38
     भरोसा
    0.37
    Casa
    0.36
     betracht
    0.36
    Activations Density 0.015%

    No Known Activations