© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233276
    Prev
    Next
    INDEX
    Explanations

    Python functions and code snippets

    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_32_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
     張
    0.36
     দর্শকের
    0.36
    张
    0.35
     flyers
    0.35
    eningen
    0.34
    장을
    0.34
    ம்பர்
    0.34
    jelen
    0.34
     vitamin
    0.34
    ᄎ
    0.34
    POSITIVE LOGITS
     Prompt
    0.38
     Sacred
    0.37
    unia
    0.37
     Воз
    0.37
    empuan
    0.36
     skulls
    0.36
    搪
    0.36
    FFECT
    0.35
     RAIL
    0.35
    छात्रा
    0.35
    Activations Density 0.001%

    No Known Activations