© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259796
    Prev
    Next
    INDEX
    Explanations

    area under a curve

    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_22_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
    от
    0.40
     anticipate
    0.37
     censored
    0.36
     responses
    0.34
     cens
    0.34
    id
    0.33
     inquiries
    0.32
    𝖆
    0.32
    예
    0.32
     intake
    0.31
    POSITIVE LOGITS
     длину
    0.43
     Villas
    0.39
     हुई
    0.38
     Ал
    0.38
     периоди
    0.38
     করিলেন
    0.38
     Doyle
    0.38
     площади
    0.38
     Plates
    0.38
    lewati
    0.38
    Activations Density 0.002%

    No Known Activations