© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29415
    Prev
    Next
    INDEX
    Explanations

    class or type

    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_40_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
     type
    0.53
    type
    0.49
    型
    0.47
    褂
    0.45
     экземпля
    0.44
     instance
    0.44
     тип
    0.44
     نوع
    0.42
     型
    0.41
     instances
    0.41
    POSITIVE LOGITS
    Un
    0.36
    Parse
    0.35
    inl
    0.35
     vat
    0.34
    Core
    0.34
     enc
    0.34
    ños
    0.34
     recomb
    0.33
     secure
    0.32
     ench
    0.32
    Activations Density 0.007%

    No Known Activations