© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225031
    Prev
    Next
    INDEX
    Explanations

    K-S, KM, KS, kg

    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_10_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
    к
    0.90
    τ
    0.70
    ウター
    0.65
    ∗</
    0.61
     पत्थर
    0.60
    х
    0.60
    np
    0.58
     δύο
    0.58
    ν
    0.58
    𝒏
    0.57
    POSITIVE LOGITS
    ที่ไม่
    0.58
    ಲೇ
    0.55
     D
    0.53
     C
    0.52
    jaro
    0.52
     seterusnya
    0.52
    /
    0.52
     Cayman
    0.52
    ...")
    0.51
     interior
    0.50
    Activations Density 0.010%

    No Known Activations