© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75105
    Prev
    Next
    INDEX
    Explanations

    data structure creation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     रिप्रोड
    0.41
     रिप्रोडक्शन
    0.39
    沙漠
    0.38
     sims
    0.37
     Bam
    0.36
     juicio
    0.36
    皘
    0.36
     ISA
    0.36
     excruciating
    0.36
     Soto
    0.35
    POSITIVE LOGITS
    getHours
    0.41
    Fallback
    0.39
    ocation
    0.38
     अंदाजा
    0.37
    Description
    0.37
    Summary
    0.37
    Guid
    0.37
    FormBorderStyle
    0.37
    走
    0.36
    nesses
    0.36
    Activations Density 0.001%

    No Known Activations