© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6487
    Prev
    Next
    INDEX
    Explanations

    createyarnSlackChromium

    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_39_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
     Savior
    0.41
    Grund
    0.39
    মূ
    0.39
    𝐽
    0.39
    LOGGER
    0.38
     Pole
    0.38
    STATEMENT
    0.38
    ന്ധ
    0.38
     Hanging
    0.38
    AVI
    0.38
    POSITIVE LOGITS
    ሽን
    0.41
     Sakurai
    0.41
    archie
    0.39
    锁
    0.39
    рья
    0.38
     ойно
    0.38
    钞
    0.37
    ereal
    0.37
    겠
    0.36
    ത്തെ
    0.35
    Activations Density 0.062%

    No Known Activations