© 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. 138697
    Prev
    Next
    INDEX
    Explanations

    for

    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
    水印
    0.38
     يمكن
    0.37
     MAXIMUM
    0.37
    punyai
    0.36
     भुवनेश्वर
    0.35
    *>(
    0.35
     voyez
    0.34
    Greater
    0.34
    urbs
    0.33
    한강
    0.33
    POSITIVE LOGITS
    戞
    0.43
     definite
    0.40
     Bxg
    0.40
     definitely
    0.39
     past
    0.38
     relic
    0.38
     alm
    0.38
    aptops
    0.38
     Duplicate
    0.38
     literature
    0.37
    Activations Density 0.001%

    No Known Activations