© 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. 150591
    Prev
    Next
    INDEX
    Explanations

    Question

    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
    Ever
    0.53
     community
    0.45
     sets
    0.44
     ever
    0.44
    ?
    0.40
    ?<
    0.37
     best
    0.36
     wore
    0.36
    Community
    0.36
    ()?
    0.36
    POSITIVE LOGITS
     Familiar
    0.51
     Helper
    0.50
     Prepare
    0.50
    员
    0.49
     Examiner
    0.48
     Round
    0.47
    round
    0.46
     Helpers
    0.46
    Round
    0.46
     round
    0.46
    Activations Density 0.000%

    No Known Activations