© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32332
    Prev
    Next
    INDEX
    Explanations

    code symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ється
    0.39
    ależy
    0.36
    ⅔
    0.34
    ه‌
    0.34
    Literal
    0.34
    Out
    0.33
    টেড
    0.33
    ⅓
    0.33
    essoal
    0.33
    ÕES
    0.33
    POSITIVE LOGITS
    ാരണ
    0.35
     Leisure
    0.34
     garbage
    0.31
    觡
    0.31
     fond
    0.31
     menina
    0.31
     miel
    0.31
     thứ
    0.31
     dazz
    0.31
     Canyon
    0.30
    Activations Density 0.010%

    No Known Activations