© 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. 123335
    Prev
    Next
    INDEX
    Explanations

    validation loss

    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
    ↵
    0.87
    و
    0.80
    allows
    0.74
     робо
    0.71
     eus
    0.67
     valida
    0.66
    ו
    0.65
    <0x8A>
    0.65
     pide
    0.65
     линия
    0.65
    POSITIVE LOGITS
    하는
    0.79
    \
    0.74
    w
    0.73
    フレー
    0.70
    ၂
    0.69
    २
    0.69
    ක්
    0.68
    은
    0.67
    2
    0.66
    З
    0.66
    Activations Density 0.000%

    No Known Activations