© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257227
    Prev
    Next
    INDEX
    Explanations

    list of services

    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_22_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
     callSettings
    0.50
    宒
    0.47
    ቂያ
    0.47
    ถี่
    0.47
    㝒
    0.46
    ㄵ
    0.45
    况
    0.45
    라고
    0.44
    乆
    0.44
    侸
    0.44
    POSITIVE LOGITS
     v
    0.57
     w
    0.52
    vre
    0.52
    iva
    0.51
     er
    0.47
    ge
    0.46
     am
    0.46
     de
    0.46
     k
    0.45
    na
    0.44
    Activations Density 0.000%

    No Known Activations