© 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. 79985
    Prev
    Next
    INDEX
    Explanations

    .

    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
     फतेह
    0.38
     السادس
    0.37
     Rick
    0.37
    حسن
    0.37
     Staffel
    0.35
    ✈
    0.35
     reconnaissance
    0.35
     sott
    0.35
     స్వ
    0.35
     refreshment
    0.35
    POSITIVE LOGITS
    abi
    0.39
    quinoxalin
    0.38
     били
    0.38
    bi
    0.37
    rosi
    0.37
    Cursors
    0.37
     domination
    0.37
    bladder
    0.35
    จีน
    0.35
    匮
    0.35
    Activations Density 0.000%

    No Known Activations