© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144080
    Prev
    Next
    INDEX
    Explanations

    recite, reciprocal, recalls, recurrent

    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_0_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
    in
    2.03
    y
    1.81
    ר
    1.68
    e
    1.57
    h
    1.57
    an
    1.52
    ק
    1.49
    ia
    1.48
    สนาม
    1.47
    한
    1.46
    POSITIVE LOGITS
    imetric
    1.14
    kę
    1.13
     linéaire
    1.13
    л
    1.13
    يل
    1.10
    ierte
    1.09
     событий
    1.05
    ляет
    1.02
    ляется
    1.02
     druga
    1.02
    Activations Density 0.000%

    No Known Activations