© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137562
    Prev
    Next
    INDEX
    Explanations

    export and import

    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_46_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
    ปาก
    0.41
     Dunn
    0.40
     reaction
    0.39
     Underwood
    0.39
     tweaked
    0.39
    ල
    0.39
    reaction
    0.38
    紳
    0.38
     বিরক্ত
    0.38
     অ্যানোডে
    0.38
    POSITIVE LOGITS
     dej
    0.38
     ডে
    0.38
     G
    0.36
     εξα
    0.36
     Vim
    0.35
     데
    0.35
     dest
    0.35
     eſ
    0.35
     забе
    0.34
    Dest
    0.34
    Activations Density 0.000%

    No Known Activations