© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 124729
    Prev
    Next
    INDEX
    Explanations

    paste into editor

    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_37_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
     jt
    0.41
     bony
    0.40
    到一个
    0.40
     જગ્યા
    0.39
     bones
    0.38
     ][
    0.38
    θ
    0.38
     joints
    0.37
    叔
    0.37
     trenches
    0.37
    POSITIVE LOGITS
     சிற
    0.40
     Smiling
    0.40
     sélection
    0.39
     නම්
    0.39
     глав
    0.38
     seleção
    0.38
    សា
    0.38
     Глав
    0.38
     ब्यूरो
    0.38
     Danh
    0.38
    Activations Density 0.004%

    No Known Activations