© 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. 146596
    Prev
    Next
    INDEX
    Explanations

    say "."

    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
     ten
    0.45
     E
    0.40
     DO
    0.39
     Ten
    0.38
     INTO
    0.38
     LL
    0.38
    ုန်
    0.38
     LE
    0.38
     Nine
    0.37
    hare
    0.37
    POSITIVE LOGITS
    .'''
    0.40
    Prov
    0.39
    ľov
    0.39
     }_{
    0.38
     реконструк
    0.38
    .$(
    0.38
    Tin
    0.38
     reconst
    0.37
    𖤐
    0.37
     주제
    0.37
    Activations Density 0.000%

    No Known Activations