© 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. 236281
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
    ති
    0.38
    舴
    0.38
    이지
    0.37
    雱
    0.36
     여성
    0.36
    راً
    0.35
     signify
    0.35
    前后
    0.35
     genitalia
    0.35
    ноп
    0.35
    POSITIVE LOGITS
     ell
    0.42
    
    0.40
    нев
    0.38
     Nevis
    0.36
    vindo
    0.36
     Bunn
    0.36
    тап
    0.35
    ushu
    0.35
    ちゃんの
    0.35
    entlichen
    0.35
    Activations Density 0.004%

    No Known Activations