© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197897
    Prev
    Next
    INDEX
    Explanations

    collateral damage

    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_12_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
     injurious
    0.64
     inscrib
    0.61
     deterioro
    0.61
    elere
    0.60
    стройство
    0.60
     endangering
    0.59
     fracturing
    0.58
     ailing
    0.58
    ত
    0.58
    षिक
    0.57
    POSITIVE LOGITS
    J
    0.70
    I
    0.69
    G
    0.67
    Sun
    0.66
    Q
    0.66
    Ø
    0.66
    Code
    0.64
    Verb
    0.64
    ).
    0.63
    Skill
    0.63
    Activations Density 0.005%

    No Known Activations