© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13624
    Prev
    Next
    INDEX
    Explanations

    my wife followed by a statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    恋爱
    0.42
    บู
    0.40
    作用
    0.39
    暉
    0.39
     Suga
    0.38
     Phon
    0.38
     Dial
    0.38
    けん
    0.38
     Thế
    0.37
     Drama
    0.36
    POSITIVE LOGITS
     ì
    0.40
     curtail
    0.39
     оператив
    0.38
    ಿಸಬಹುದು
    0.37
    ["
    0.37
    ឧប
    0.37
     religiously
    0.36
     legally
    0.36
     ବ
    0.36
     [,
    0.36
    Activations Density 0.001%

    No Known Activations