© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37264
    Prev
    Next
    INDEX
    Explanations

    major cause, risk, factor, clue, component

    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_11_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
    improved
    0.64
    been
    0.60
    Improved
    0.59
    া
    0.57
     adhesion
    0.57
    Miguel
    0.57
     Pietro
    0.56
    Improve
    0.55
    Sicilian
    0.55
     Filippo
    0.55
    POSITIVE LOGITS
     entidade
    0.57
     invál
    0.53
     misdeme
    0.51
     esclare
    0.50
     эмо
    0.50
    ก
    0.50
    ьи
    0.49
     musically
    0.49
    <unused1007>
    0.49
    тке
    0.49
    Activations Density 0.006%

    No Known Activations