© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238369
    Prev
    Next
    INDEX
    Explanations

    planets in order

    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_25_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
    thiop
    0.40
    </h2>
    0.39
     all
    0.39
     Saba
    0.39
     Parisian
    0.38
     magma
    0.38
     mand
    0.38
     maintien
    0.38
    თვის
    0.38
     Brussels
    0.37
    POSITIVE LOGITS
    miR
    0.42
    钤
    0.42
     sistemat
    0.40
    getFlight
    0.38
     ବି
    0.38
    य्
    0.38
    寤
    0.38
    ựng
    0.38
    समय
    0.38
    ublik
    0.37
    Activations Density 0.001%

    No Known Activations