© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145154
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ة
    1.46
    ;
    1.41
    ED
    1.37
    ,
    1.37
     as
    1.23
    I
    1.22
    에
    1.20
    ge
    1.17
    RE
    1.16
    alls
    1.16
    POSITIVE LOGITS
    د
    2.06
    v
    1.86
    r
    1.76
    on
    1.58
    il
    1.52
     on
    1.48
    ről
    1.42
    ד
    1.42
    m
    1.41
    ів
    1.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.