© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134516
    Prev
    Next
    INDEX
    Explanations

    chilled

    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_1_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
     as
    1.56
    1
    1.31
    o
    1.19
    +
    1.13
    _
    1.11
    ul
    1.10
    ;
    1.09
    as
    1.08
    SO
    1.07
    :
    1.07
    POSITIVE LOGITS
     manquer
    1.25
    نی
    1.18
    ин
    1.11
    الی
    1.09
    ле
    1.05
     sprouting
    1.05
    angkat
    1.03
    י
    1.02
    ровать
    1.02
    يان
    1.02
    Activations Density 0.000%

    No Known Activations