© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56591
    Prev
    Next
    INDEX
    Explanations

    speculate

    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_11_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
    ד
    0.55
     JANUARY
    0.55
     FEBRUARY
    0.54
     문제는
    0.54
     ສຳ
    0.54
     Bedürfn
    0.53
    ලි
    0.53
     bhfu
    0.53
    Ấ
    0.53
    ജ
    0.52
    POSITIVE LOGITS
     pounding
    0.49
     batting
    0.47
     blogging
    0.46
     dike
    0.44
     tidal
    0.43
     preaching
    0.43
     collar
    0.42
     revolving
    0.41
     multiplier
    0.41
     preacher
    0.41
    Activations Density 0.000%

    No Known Activations