© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36026
    Prev
    Next
    INDEX
    Explanations

    emoticon faces ^_^ >w<

    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_11_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
     holde
    0.62
    ckte
    0.55
     settle
    0.54
    liy
    0.54
    其
    0.54
     laag
    0.53
    ানা
    0.53
     mitigate
    0.52
     waxay
    0.52
    ajer
    0.52
    POSITIVE LOGITS
    ،
    0.84
    ر
    0.79
    ፣
    0.65
    ي
    0.63
    →
    0.63
    il
    0.62
    elics
    0.60
    ，
    0.59
    Я
    0.59
     Въ
    0.59
    Activations Density 0.003%

    No Known Activations