© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79815
    Prev
    Next
    INDEX
    Explanations

    say less

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    hemer
    0.38
    пере
    0.34
    ต
    0.34
     plaintext
    0.34
     Cly
    0.34
    ponential
    0.33
    jou
    0.33
    zey
    0.33
    rarea
    0.33
    广
    0.33
    POSITIVE LOGITS
    Leslie
    1.27
     Leslie
    1.27
     LES
    1.15
     Lesley
    1.15
     les
    1.10
    les
    1.08
    LES
    1.02
    Les
    1.02
     Les
    1.01
     Lesotho
    0.95
    Activations Density 0.002%

    No Known Activations