© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34563
    Prev
    Next
    INDEX
    Explanations

    meeting specific criteria

    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_31_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
    isOn
    0.25
     forfeited
    0.24
     violation
    0.24
    斡
    0.24
     sva
    0.24
     Expert
    0.23
     desires
    0.23
     athleticism
    0.23
     expert
    0.22
     violated
    0.22
    POSITIVE LOGITS
     Worte
    0.27
    talking
    0.24
     정책
    0.23
    詞
    0.23
    গাল
    0.23
     ngũ
    0.22
     வெளியிட
    0.22
    acent
    0.22
     piek
    0.22
    ensch
    0.22
    Activations Density 0.012%

    No Known Activations