© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86334
    Prev
    Next
    INDEX
    Explanations

    dates and code punctuation

    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_23_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
    Л
    0.43
    L
    0.42
    In
    0.41
    Use
    0.40
    H
    0.40
    eken
    0.40
    key
    0.39
    ez
    0.39
    ક
    0.38
    All
    0.38
    POSITIVE LOGITS
     görd
    0.45
     criaturas
    0.42
     consigo
    0.42
     frontière
    0.42
     bloke
    0.40
    膂
    0.40
     entrevistas
    0.39
     unwitting
    0.39
     doings
    0.39
     அவர்களுடைய
    0.39
    Activations Density 0.000%

    No Known Activations