© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28581
    Prev
    Next
    INDEX
    Explanations

    "stated", "explained", "said", "muttered", "rasped", "mumbled"

    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_40_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
     say
    0.38
     번
    0.36
     she
    0.35
     doctor
    0.35
     cs
    0.35
    她说
    0.35
     Yu
    0.35
     Miguel
    0.34
     Hu
    0.34
    つつ
    0.34
    POSITIVE LOGITS
    entrale
    0.38
    })`;
    0.38
    Tile
    0.36
    Fade
    0.35
    тік
    0.31
    }</
    0.31
    FileInputExcel
    0.31
    स्त
    0.31
    Circle
    0.31
     Stripe
    0.31
    Activations Density 0.004%

    No Known Activations