© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207483
    Prev
    Next
    INDEX
    Explanations

    inconsistent / consistency

    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_25_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
     Caruso
    0.39
     расход
    0.39
     BO
    0.38
     underwriting
    0.38
     Derbyshire
    0.38
     ব্যবহারের
    0.37
    jne
    0.36
    
    0.35
     Pars
    0.35
     Unsupported
    0.34
    POSITIVE LOGITS
     modalCard
    0.37
     bhij
    0.36
    ovno
    0.35
     %>%
    0.34
     veil
    0.34
    gelopen
    0.34
    ველ
    0.33
     laporan
    0.33
     eul
    0.33
     තුළ
    0.33
    Activations Density 0.002%

    No Known Activations