© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204013
    Prev
    Next
    INDEX
    Explanations

    SQL auto-increment keywords

    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_25_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
    ্যানের
    0.39
    厈
    0.38
    กีฬา
    0.35
    専門
    0.35
    ্যান
    0.34
    alaikums
    0.33
    歯科
    0.33
     forestry
    0.33
    LIS
    0.32
     dutiful
    0.32
    POSITIVE LOGITS
    里
    0.40
     portare
    0.39
     belong
    0.37
    েলি
    0.37
     ي
    0.37
     cerrar
    0.36
    ຢູ່ໃນ
    0.36
     belongs
    0.35
    Ag
    0.35
    anje
    0.35
    Activations Density 0.001%

    No Known Activations