© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34915
    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_31_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
    ሽታ
    0.33
    asak
    0.33
    ioni
    0.32
    ibar
    0.32
    Listo
    0.32
     rollerskates
    0.31
    牲
    0.31
    ഷ്ട
    0.31
    ensee
    0.31
     Ozzy
    0.31
    POSITIVE LOGITS
     juríd
    0.35
    اقة
    0.34
     aDict
    0.34
    雕
    0.31
    ENTRY
    0.30
    eclipse
    0.30
    理念
    0.30
    enumeration
    0.30
     carve
    0.29
    права
    0.29
    Activations Density 0.000%

    No Known Activations