© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34924
    Prev
    Next
    INDEX
    Explanations

    raw

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    枌
    0.46
     Brush
    0.42
     Российской
    0.40
    🧑
    0.40
     cyclohex
    0.39
     активно
    0.39
     bouche
    0.39
    睒
    0.38
    突
    0.38
    чів
    0.38
    POSITIVE LOGITS
     raw
    0.53
    raw
    0.47
    mus
    0.47
     RAW
    0.45
     Raw
    0.43
    Thro
    0.43
    Raw
    0.41
    rawValue
    0.40
    原料
    0.40
    Billing
    0.40
    Activations Density 0.018%

    No Known Activations