© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38233
    Prev
    Next
    INDEX
    Explanations

    I

    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_57_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
    รูป
    0.39
    }">
    0.39
    తన
    0.37
    磅
    0.36
    convert
    0.35
     haber
    0.35
    することは
    0.35
     உற்ச
    0.35
    嫣
    0.34
    Rit
    0.34
    POSITIVE LOGITS
    ᴵ
    0.43
    イ
    0.40
    ζί
    0.40
    dehyde
    0.40
    恫
    0.39
    אי
    0.39
    azał
    0.38
    ibet
    0.37
    icile
    0.36
    覺
    0.36
    Activations Density 0.043%

    No Known Activations