© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172808
    Prev
    Next
    INDEX
    Explanations

    names of places, events, or types of backups

    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_20_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
     които
    0.31
     Cuff
    0.30
    willing
    0.29
     unwillingness
    0.29
     Curiosity
    0.28
     నిజ
    0.28
     ktorí
    0.28
     久
    0.28
    possibleTypes
    0.28
    FBSDKSettings
    0.27
    POSITIVE LOGITS
    rary
    0.31
    </tr>
    0.29
    lux
    0.29
    you
    0.29
    ye
    0.29
    ığınız
    0.28
     installments
    0.27
     dosy
    0.27
     you
    0.26
    ruct
    0.26
    Activations Density 0.000%

    No Known Activations