© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53698
    Prev
    Next
    INDEX
    Explanations

    state and data

    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_55_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
     low
    0.57
    低
    0.50
     저
    0.49
     background
    0.48
     Low
    0.46
     backgrounds
    0.46
     operations
    0.45
    系
    0.45
     retrieval
    0.44
     низ
    0.44
    POSITIVE LOGITS
     Pache
    0.39
    诌
    0.38
     Nase
    0.38
    ScriptObject
    0.37
    erina
    0.37
    ત્મ
    0.36
    InData
    0.36
    conn
    0.36
    Digite
    0.36
     falsa
    0.35
    Activations Density 0.065%

    No Known Activations