© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207440
    Prev
    Next
    INDEX
    Explanations

    file: operations

    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_20_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
     ALLO
    0.44
     Allo
    0.43
     Toen
    0.43
     october
    0.42
     オール
    0.42
     inp
    0.42
     Π
    0.40
     Toe
    0.39
     Ο
    0.39
     העולם
    0.39
    POSITIVE LOGITS
    áh
    0.46
     命令
    0.44
    电子
    0.41
    JPY
    0.40
    éb
    0.39
    готовки
    0.39
    वरून
    0.39
     електрон
    0.39
    ück
    0.38
    erek
    0.38
    Activations Density 0.001%

    No Known Activations