© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30868
    Prev
    Next
    INDEX
    Explanations

    origin and etymology

    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_31_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
    クター
    0.39
     psych
    0.35
     Psych
    0.34
    冨
    0.33
     연속
    0.33
    ెంట్
    0.33
     psychopath
    0.33
     ricor
    0.33
     Continuation
    0.33
     bý
    0.32
    POSITIVE LOGITS
    ၽ
    0.42
    middleware
    0.42
    rewsbury
    0.41
    足
    0.40
     athletics
    0.39
    rowse
    0.37
     Asante
    0.37
    瀨
    0.37
     منص
    0.36
     Londra
    0.36
    Activations Density 0.025%

    No Known Activations