© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57803
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    嗐
    0.42
    SetStr
    0.40
     ን
    0.39
    മായി
    0.39
    愫
    0.39
     הר
    0.38
     Discharge
    0.38
    MessageNow
    0.38
    RunWith
    0.38
    Strat
    0.38
    POSITIVE LOGITS
    first
    0.50
     K
    0.43
    regex
    0.42
    **
    0.42
    recipe
    0.41
    commander
    0.41
    opsis
    0.39
    k
    0.39
     first
    0.39
    utility
    0.39
    Activations Density 0.000%

    No Known Activations