© 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. 235545
    Prev
    Next
    INDEX
    Explanations

    private

    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
    ਲੀ
    0.38
     Gol
    0.38
    삭
    0.36
     ild
    0.35
     ஆய
    0.34
    alda
    0.34
     SUST
    0.33
     Reuben
    0.33
    孝
    0.33
    들을
    0.33
    POSITIVE LOGITS
     detective
    1.33
     detectives
    1.23
     Detective
    1.12
    Detective
    1.09
     Detect
    0.99
    detect
    0.92
     detect
    0.89
     détect
    0.88
    Detect
    0.87
    侦
    0.86
    Activations Density 0.001%

    No Known Activations