© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53975
    Prev
    Next
    INDEX
    Explanations

    prior information

    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_55_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
    سے
    0.39
    舧
    0.37
    상품
    0.36
    تما
    0.34
     ።
    0.34
     গমন
    0.34
     Cul
    0.34
     Расійскай
    0.34
    뺨
    0.34
    क्रम
    0.33
    POSITIVE LOGITS
     prior
    0.89
     provided
    0.85
     prompt
    0.80
     given
    0.74
     problem
    0.72
    prior
    0.69
    Prior
    0.67
    provided
    0.67
    prompt
    0.66
     Provided
    0.64
    Activations Density 0.016%

    No Known Activations