© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199010
    Prev
    Next
    INDEX
    Explanations

    turtle

    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_9_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
    は
    1.45
    on
    1.22
    に
    1.13
    که
    1.11
    ۔
    1.08
    ון
    1.07
    '
    1.06
    が
    1.03
    t
    1.02
    erà
    1.01
    POSITIVE LOGITS
     New
    0.86
    л
    0.86
     Transportation
    0.83
     Man
    0.82
     Method
    0.81
    د
    0.80
     తిన
    0.79
     Bios
    0.79
    bog
    0.79
     List
    0.78
    Activations Density 0.001%

    No Known Activations