© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44651
    Prev
    Next
    INDEX
    Explanations

    Redux store configuration

    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_22_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
    涝
    0.42
     میکر
    0.42
     באמצעות
    0.41
     كن
    0.41
     зоны
    0.40
     параметры
    0.40
     зона
    0.39
     gì
    0.38
     новая
    0.38
     Turf
    0.38
    POSITIVE LOGITS
     anbef
    0.49
    Critic
    0.45
     underestimated
    0.45
    漃
    0.43
     Critic
    0.42
    批評
    0.42
     Criticism
    0.42
     McIntyre
    0.42
     ഇടതു
    0.42
    Critics
    0.41
    Activations Density 0.000%

    No Known Activations