© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86585
    Prev
    Next
    INDEX
    Explanations

    website paths and code definitions

    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_23_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
    ült
    0.33
     nélkül
    0.31
    金属
    0.31
     모습을
    0.31
    metal
    0.30
     метал
    0.30
     manner
    0.29
     ድ
    0.29
    ilder
    0.29
     metal
    0.29
    POSITIVE LOGITS
     Zone
    0.31
     ZONE
    0.31
     reff
    0.30
    remember
    0.30
    ுகிறார்கள்
    0.30
     {}\
    0.29
    credential
    0.29
    也就
    0.29
    ۖ
    0.29
     commerciali
    0.28
    Activations Density 0.006%

    No Known Activations