© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40145
    Prev
    Next
    INDEX
    Explanations

    symbols and numbers

    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_57_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
     tongue
    0.33
    quakes
    0.32
    comings
    0.31
     jaws
    0.31
     world
    0.30
    𝖽
    0.30
     haces
    0.29
    dear
    0.29
     interested
    0.28
     unpacking
    0.28
    POSITIVE LOGITS
    urnal
    0.32
    迺
    0.32
    ostics
    0.31
     فوټبال
    0.29
     गुणा
    0.29
    鈮
    0.28
    urais
    0.28
     спорттук
    0.28
    落实
    0.27
    徴
    0.27
    Activations Density 0.030%

    No Known Activations