© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210166
    Prev
    Next
    INDEX
    Explanations

    numbers and durations

    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_43_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
     మరి
    0.40
     ander
    0.40
     لپ
    0.40
     Cál
    0.39
    还可以
    0.39
    Teller
    0.38
    ⁵
    0.38
    mai
    0.38
    涹
    0.38
    <unused57>
    0.37
    POSITIVE LOGITS
    емов
    0.39
    ethi
    0.38
    ക്ത
    0.37
    牛肉
    0.37
    iss
    0.36
    วจ
    0.35
    ኚ
    0.35
     小物
    0.34
    व्यव
    0.34
    мор
    0.33
    Activations Density 0.000%

    No Known Activations