© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79005
    Prev
    Next
    INDEX
    Explanations

    словацкая, украинская, сербская, португальская, испанская, хинди

    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_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
    し
    1.61
    ске
    1.45
    其他
    1.33
    м
    1.31
    тың
    1.27
    с
    1.23
    ához
    1.20
     asegur
    1.19
    к
    1.19
    िक
    1.18
    POSITIVE LOGITS
    _
    2.34
     by
    2.05
    {
    1.95
    3
    1.90
    \
    1.84
    $
    1.78
    0
    1.74
    P
    1.66
    O
    1.66
    ן
    1.63
    Activations Density 0.000%

    No Known Activations