© 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. 49567
    Prev
    Next
    INDEX
    Explanations

    definite indefinite

    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
     canal
    0.39
    canal
    0.38
     lift
    0.37
     fires
    0.36
    新型
    0.36
     replaces
    0.36
     lifts
    0.36
    ϭ
    0.35
    ise
    0.34
     Banner
    0.34
    POSITIVE LOGITS
    tał
    0.39
    ał
    0.38
    amit
    0.38
    вата
    0.38
    mselves
    0.38
    ামে
    0.38
    iata
    0.38
     Mortara
    0.38
     Initialization
    0.38
     પ્રતિબ
    0.37
    Activations Density 0.001%

    No Known Activations