© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39329
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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_3_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
    ۳
    0.88
     rozwiąz
    0.75
     یخ
    0.72
    変更
    0.70
    ަނ
    0.70
    חד
    0.68
    鋲
    0.68
    ۹
    0.67
    た
    0.66
    ご注意
    0.66
    POSITIVE LOGITS
    ik
    0.79
    ü
    0.72
    O
    0.70
    istik
    0.70
    atak
    0.67
    ust
    0.66
    ing
    0.66
    uden
    0.65
    ude
    0.65
    eller
    0.64
    Activations Density 0.003%

    No Known Activations