© 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. 202760
    Prev
    Next
    INDEX
    Explanations

    localhost

    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
    減
    0.38
     रोप
    0.38
    Reducing
    0.37
    Dest
    0.36
     சிகி
    0.36
    Gross
    0.36
    NOP
    0.36
    Veget
    0.35
    restrict
    0.35
    Developed
    0.35
    POSITIVE LOGITS
    季
    0.43
     ports
    0.41
     portability
    0.40
     humanidad
    0.40
     outfield
    0.39
    芯片
    0.39
     port
    0.39
     season
    0.38
     सीजन
    0.38
     luminosity
    0.38
    Activations Density 0.001%

    No Known Activations