© 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. 64115
    Prev
    Next
    INDEX
    Explanations

    places and entities

    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
     Para
    0.82
    Para
    0.79
    头
    0.76
    頭
    0.74
    PARA
    0.73
    para
    0.72
    头的
    0.72
     para
    0.69
    пара
    0.68
     पैरा
    0.67
    POSITIVE LOGITS
     coagulation
    0.41
     silence
    0.37
    SECOND
    0.37
    존
    0.37
     volume
    0.35
    齐
    0.35
     ബ്രി
    0.35
    צב
    0.35
     WEBSITE
    0.35
    क्रो
    0.34
    Activations Density 0.002%

    No Known Activations