© 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. 165570
    Prev
    Next
    INDEX
    Explanations

    June and months

    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
    wast
    0.35
    conditional
    0.33
    Swap
    0.33
    ப்த
    0.33
    Compensation
    0.33
    acelet
    0.33
     Swap
    0.32
    揀
    0.32
     conditional
    0.31
    skins
    0.30
    POSITIVE LOGITS
     buccal
    0.36
     fourth
    0.34
    字
    0.34
     buried
    0.33
     litt
    0.33
     nucleotide
    0.33
     nineties
    0.33
    柠檬
    0.32
     essen
    0.32
     Metabol
    0.32
    Activations Density 0.000%

    No Known Activations