© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26889
    Prev
    Next
    INDEX
    Explanations

    Point of View

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    Corpor
    0.50
     Neur
    0.47
    Neur
    0.44
     jeopardize
    0.44
    PathResource
    0.43
     بوس
    0.42
    <unused2141>
    0.42
    uberculosis
    0.41
    Pseudo
    0.41
     ()
    0.41
    POSITIVE LOGITS
    a
    0.60
    γων
    0.55
    一緒に
    0.51
    iding
    0.51
    on
    0.50
    iy
    0.49
    j
    0.49
    el
    0.47
    an
    0.46
     clove
    0.46
    Activations Density 0.000%

    No Known Activations