© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61113
    Prev
    Next
    INDEX
    Explanations

    I

    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
    拝
    0.50
     apolog
    0.42
     ആയി
    0.40
    setRequest
    0.39
     সোভিয়ে
    0.39
    adikan
    0.38
     apology
    0.37
    sorry
    0.37
     собе
    0.37
    <unused557>
    0.36
    POSITIVE LOGITS
    失
    1.61
     afraid
    1.18
     失
    1.18
     Lost
    0.75
     Loss
    0.68
    Lost
    0.67
     loss
    0.66
     lost
    0.66
    Loss
    0.64
     LOST
    0.62
    Activations Density 0.009%

    No Known Activations