© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97966
    Prev
    Next
    INDEX
    Explanations

    primary source accounts

    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_14_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ล
    0.54
    े
    0.50
    older
    0.49
    u
    0.49
     they
    0.43
     tumor
    0.43
     everyone
    0.42
    ujen
    0.41
    ल
    0.41
     spinal
    0.41
    POSITIVE LOGITS
    鎏
    0.51
    Accounts
    0.49
     був
    0.49
     ク
    0.48
     Descriptions
    0.47
     Specifications
    0.47
    Vault
    0.46
    スペック
    0.46
     Description
    0.46
     Vault
    0.46
    Activations Density 0.003%

    No Known Activations