© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205460
    Prev
    Next
    INDEX
    Explanations

    key

    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
    )【
    0.43
    ,'"
    0.43
    ),"
    0.43
    ),”
    0.42
    )[
    0.41
    ,~
    0.40
    atação
    0.40
    )==
    0.39
    )!=
    0.39
    ,)
    0.39
    POSITIVE LOGITS
     :
    0.42
     empresa
    0.40
     routes
    0.38
    قليم
    0.38
    兘
    0.37
    routes
    0.37
    ும்
    0.36
    ყენ
    0.36
    restaurants
    0.36
    PageRoute
    0.36
    Activations Density 0.001%

    No Known Activations