© 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. 138601
    Prev
    Next
    INDEX
    Explanations

    academic resources linguistics

    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
    স্তে
    0.39
     dean
    0.38
     Semester
    0.38
     medic
    0.38
    Dean
    0.38
    🐱
    0.38
    breed
    0.37
    企
    0.37
     Seda
    0.37
     Toot
    0.37
    POSITIVE LOGITS
     gs
    0.44
     GSE
    0.43
     글
    0.39
    リム
    0.39
     جل
    0.39
    tls
    0.38
    IMM
    0.38
    TLS
    0.37
     precipitated
    0.37
     GS
    0.36
    Activations Density 0.001%

    No Known Activations