© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123262
    Prev
    Next
    INDEX
    Explanations

    Swift previews and workflows

    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
     केन्द्र
    0.39
     wrestled
    0.39
     photographers
    0.38
    бла
    0.37
    츨
    0.37
     Фото
    0.37
    ListItem
    0.36
     Mountaine
    0.36
    AMS
    0.36
     hiked
    0.35
    POSITIVE LOGITS
    怡
    0.42
     ശി
    0.41
    شم
    0.40
     induce
    0.39
    agama
    0.38
    cycline
    0.38
     cur
    0.37
    方法的
    0.37
     introd
    0.37
    汋
    0.36
    Activations Density 0.000%

    No Known Activations