© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206197
    Prev
    Next
    INDEX
    Explanations

    Safety Data Sheets (SDS)

    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_19_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
    权益
    0.49
    dirname
    0.46
    dai
    0.46
    daa
    0.45
    aton
    0.45
    dach
    0.45
    :]:
    0.45
    allaitement
    0.45
    얹
    0.45
    tat
    0.44
    POSITIVE LOGITS
     ideological
    0.47
     CIA
    0.47
     Barrios
    0.46
     behavioural
    0.46
     consulted
    0.46
     accepted
    0.45
     contrast
    0.45
     conceded
    0.45
     ideas
    0.44
     schools
    0.44
    Activations Density 0.001%

    No Known Activations