© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115084
    Prev
    Next
    INDEX
    Explanations

    summary of

    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_27_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
     구독
    0.42
     undergo
    0.39
     库存
    0.37
    icionado
    0.37
     сле
    0.36
     atend
    0.33
    ...@
    0.33
    这将
    0.33
    গম
    0.33
     देखता
    0.33
    POSITIVE LOGITS
     sentimientos
    0.39
    ূল্যে
    0.38
     Talking
    0.38
     AMOUNT
    0.38
    ChatItem
    0.37
    داء
    0.37
     Aide
    0.37
     enfermedades
    0.37
     Seng
    0.37
    धीश
    0.36
    Activations Density 0.016%

    No Known Activations