© 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. 33215
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    xas
    0.40
    셔
    0.40
    ทยาลัย
    0.38
     AVEN
    0.38
    obt
    0.37
    喔
    0.36
    pere
    0.35
     Nort
    0.35
    ಿಸಿದ್ದಾರೆ
    0.35
    assemble
    0.35
    POSITIVE LOGITS
    antha
    0.38
    arıyla
    0.36
     lotus
    0.36
    setUser
    0.35
    手が
    0.35
    恒
    0.35
     cookie
    0.35
    setScene
    0.35
     Surprise
    0.34
    客人
    0.34
    Activations Density 0.000%

    No Known Activations