© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104162
    Prev
    Next
    INDEX
    Explanations

    greeter

    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_1_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
     I
    1.38
    IS
    1.19
    า
    1.16
     can
    1.13
     B
    1.10
     J
    1.10
     U
    1.10
    е
    1.10
     V
    1.09
    ON
    1.07
    POSITIVE LOGITS
    ل
    1.53
    h
    1.52
    म
    1.38
    ल
    1.38
    toadd
    1.37
    ت
    1.32
     інших
    1.31
    to
    1.29
    the
    1.23
    hā
    1.23
    Activations Density 0.000%

    No Known Activations