© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195646
    Prev
    Next
    INDEX
    Explanations

    Modern, Minimalist, Tech, Third

    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_27_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
     favors
    0.31
     frontage
    0.30
     necessities
    0.29
     chord
    0.29
     expans
    0.28
     sleeve
    0.28
    ?]
    0.28
     using
    0.28
     deserunt
    0.27
     बिगड़
    0.27
    POSITIVE LOGITS
    每一次
    0.33
     সর্বাধিক
    0.32
    酵
    0.31
    Template
    0.29
    ายุ
    0.29
    rierte
    0.29
     Almost
    0.29
     разби
    0.29
    RawContext
    0.29
    úz
    0.28
    Activations Density 0.014%

    No Known Activations