© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1229
    Prev
    Next
    INDEX
    Explanations

    data preprocessing and preparation

    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_39_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
     pokuš
    0.37
     Sheikh
    0.36
    గర
    0.36
     うん
    0.35
    Sheikh
    0.34
    ემის
    0.34
    作者
    0.33
    鴨
    0.33
     Equity
    0.32
     Roja
    0.32
    POSITIVE LOGITS
     preprocessing
    1.41
    Preprocessing
    1.38
     preprocess
    1.26
    preprocessing
    1.20
    preprocess
    1.17
    Preprocessor
    1.05
     processing
    1.00
     pretreatment
    0.97
     Pre
    0.93
     Processing
    0.92
    Activations Density 0.347%

    No Known Activations