© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37465
    Prev
    Next
    INDEX
    Explanations

    wrapping or covering with hands

    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
     narrowband
    0.57
    </h3>
    0.55
     widescreen
    0.54
     horizontally
    0.54
     daemon
    0.54
    рья
    0.54
    ないと
    0.54
     επ
    0.53
    ቕ
    0.53
    勮
    0.53
    POSITIVE LOGITS
    on
    0.76
    0
    0.61
    he
    0.55
    slate
    0.55
    ang
    0.55
    en
    0.55
    mt
    0.53
    am
    0.52
    ı
    0.52
    ent
    0.52
    Activations Density 0.042%

    No Known Activations