© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246404
    Prev
    Next
    INDEX
    Explanations

    japanese and web technologies

    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_40_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
    工业
    0.46
    Mats
    0.40
     junk
    0.39
     Marathi
    0.38
     Satoshi
    0.37
     courthouse
    0.37
    ⬥
    0.37
    涹
    0.37
    കര
    0.36
     traffic
    0.36
    POSITIVE LOGITS
    uyan
    0.37
    անդ
    0.37
     품
    0.36
    apeti
    0.35
    型
    0.35
    aphr
    0.34
     형
    0.34
     وط
    0.33
    Fet
    0.33
     확보
    0.33
    Activations Density 0.000%

    No Known Activations