© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179792
    Prev
    Next
    INDEX
    Explanations

    Departments and services

    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_29_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
     Improvement
    0.37
     범위
    0.36
    FixedWidth
    0.35
    cstdlib
    0.35
    iciente
    0.35
     ഓരോ
    0.35
    율
    0.35
     io
    0.34
     chunks
    0.33
    तीन
    0.33
    POSITIVE LOGITS
    dey
    0.44
     Duffy
    0.42
    
    0.39
    GeneratedValue
    0.39
    decken
    0.38
    徳
    0.38
    𝗮
    0.38
     knocking
    0.37
    centre
    0.37
    レンチ
    0.36
    Activations Density 0.009%

    No Known Activations