© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20465
    Prev
    Next
    INDEX
    Explanations

    id

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    s
    0.45
    ের
    0.45
    ುವುದಿಲ್ಲ
    0.44
    ો
    0.43
    o
    0.42
    ی
    0.40
    dale
    0.39
    ು
    0.39
    aer
    0.39
    ﻔ
    0.38
    POSITIVE LOGITS
    ଼
    0.73
    raulic
    0.71
    oubt
    0.59
    ifferent
    0.57
    irectional
    0.54
    žių
    0.54
    ividual
    0.52
    etailed
    0.52
    elivery
    0.52
    ivided
    0.52
    Activations Density 0.019%

    No Known Activations