© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26253
    Prev
    Next
    INDEX
    Explanations

    how much

    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_10_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
     effectuées
    0.65
    िंग
    0.64
    until
    0.64
    ة
    0.64
    𝗱
    0.63
    愭
    0.62
    نی
    0.61
    killing
    0.61
    dyl
    0.61
    overs
    0.61
    POSITIVE LOGITS
    EN
    0.69
     $
    0.65
    ymmetry
    0.65
     an
    0.61
     вза
    0.58
     es
    0.57
    OCH
    0.57
     la
    0.57
    ES
    0.56
     prote
    0.55
    Activations Density 0.037%

    No Known Activations