© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14321
    Prev
    Next
    INDEX
    Explanations

    Fields, Map, Numeria

    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_13_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
    sudo
    0.44
    ური
    0.44
     cable
    0.42
    Что
    0.40
    <em>
    0.40
     lad
    0.40
     snakes
    0.40
    劦
    0.40
     Dug
    0.39
    ated
    0.39
    POSITIVE LOGITS
     Ừ
    0.64
     द्रविड़
    0.59
     ମ
    0.56
    irlik
    0.53
     EHR
    0.53
    ленд
    0.53
     τ
    0.52
     एनसीआरटी
    0.52
    ennzeichnet
    0.52
    沌
    0.52
    Activations Density 0.000%

    No Known Activations