© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81773
    Prev
    Next
    INDEX
    Explanations

    corroborated by

    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_0_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
    م
    2.30
    n
    2.22
    ad
    1.85
    at
    1.71
    il
    1.67
    ش
    1.67
    the
    1.66
    ER
    1.64
    RO
    1.61
    art
    1.59
    POSITIVE LOGITS
    ない
    1.59
    }{
    1.31
    行う
    1.31
     insistent
    1.28
    いた
    1.26
    ができる
    1.24
     severed
    1.23
     июня
    1.23
     excised
    1.20
    ९
    1.13
    Activations Density 0.000%

    No Known Activations