© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62362
    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
     a
    0.46
     The
    0.41
    The
    0.39
     justifyContent
    0.38
     দ্য
    0.36
     go
    0.36
    Direction
    0.35
    collision
    0.35
    ="../
    0.34
     अमन
    0.34
    POSITIVE LOGITS
     Be
    0.76
     A
    0.72
    Be
    0.67
     Of
    0.64
     Best
    0.62
    have
    0.55
     An
    0.54
     For
    0.54
    Of
    0.52
    A
    0.50
    Activations Density 0.021%

    No Known Activations