© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59881
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    屣
    0.36
     zaidi
    0.33
     ලද
    0.32
    穸
    0.32
     lucru
    0.32
    меня
    0.31
     മാത്ര
    0.31
     മാത്രമല്ല
    0.31
     වීම
    0.31
    PlatformTarget
    0.31
    POSITIVE LOGITS
    ,
    1.80
    {,}
    1.22
    ،
    1.16
    ٬
    1.16
     ,
    1.15
    ,/
    1.15
    ,<
    1.12
    ,.
    1.09
    ፣
    1.08
    ,\
    1.06
    Activations Density 0.370%

    No Known Activations