© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8952
    Prev
    Next
    INDEX
    Explanations

    function call

    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_13_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
     Materialien
    0.54
     পর
    0.43
     Ishikawa
    0.42
     Tattha
    0.41
     ಎರ
    0.41
     ครับ
    0.41
     ০
    0.41
     обще
    0.40
     $\%
    0.40
     Reactors
    0.40
    POSITIVE LOGITS
    tr
    0.55
    //
    0.50
    d
    0.50
    h
    0.49
    w
    0.48
    br
    0.47
    전
    0.44
     as
    0.44
    call
    0.43
    Call
    0.43
    Activations Density 0.034%

    No Known Activations