© 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. 122982
    Prev
    Next
    INDEX
    Explanations

    sklearn metrics import

    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
    ↵
    0.65
    THER
    0.59
     mendapatkan
    0.59
     amiga
    0.57
    RAEL
    0.57
    ATE
    0.56
     ‘
    0.55
     uses
    0.55
    UB
    0.55
    EMENT
    0.55
    POSITIVE LOGITS
    е
    0.76
    يل
    0.71
    ло
    0.70
    ви
    0.69
    خ
    0.68
    ان
    0.68
    وم
    0.66
    知
    0.64
    ليل
    0.64
    ennzeichnet
    0.63
    Activations Density 0.001%

    No Known Activations