© 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. 75152
    Prev
    Next
    INDEX
    Explanations

    double helix

    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
     vazio
    0.42
     Genomic
    0.39
     processors
    0.38
     часы
    0.36
    Seconds
    0.35
    怛
    0.35
    細胞
    0.35
    앵
    0.35
     ATMs
    0.34
    चु
    0.34
    POSITIVE LOGITS
     lh
    0.39
     ui
    0.37
     abstract
    0.36
     BUN
    0.36
    阌
    0.35
    COMPILE
    0.35
     Racine
    0.35
    ++
    0.34
    移民
    0.34
     folds
    0.34
    Activations Density 0.003%

    No Known Activations