© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20810
    Prev
    Next
    INDEX
    Explanations

    shy

    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_56_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
     sh
    3.00
    sh
    1.85
     Sh
    1.80
     ش
    1.73
    Sh
    1.58
     ш
    1.47
     श
    1.46
     শ
    1.46
    し
    1.27
     shunt
    1.20
    POSITIVE LOGITS
     pem
    0.48
    +][
    0.38
    呱
    0.37
     Pem
    0.37
    ędz
    0.36
    레스
    0.35
    ochen
    0.35
    ডো
    0.34
    lis
    0.33
     বোমা
    0.33
    Activations Density 0.026%

    No Known Activations