© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59778
    Prev
    Next
    INDEX
    Explanations

    }

    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_59_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
    тих
    0.42
    ilación
    0.42
    :
    0.41
    같
    0.41
     ?"
    0.41
    ？”
    0.40
     ?",
    0.40
     !",
    0.40
    ваны
    0.39
    ?"
    0.38
    POSITIVE LOGITS
    Cell
    0.44
    ^
    0.43
     /
    0.42
    -${
    0.42
    **
    0.42
     ${
    0.41
    ®
    0.41
    Ad
    0.40
    rd
    0.40
    gran
    0.40
    Activations Density 0.001%

    No Known Activations