© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34931
    Prev
    Next
    INDEX
    Explanations

    ~/.config/ or ~/.ssh/

    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_31_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
     эффектив
    0.43
    tones
    0.41
    hets
    0.40
    Ejercicio
    0.39
     فبراير
    0.39
     эффективно
    0.39
    enseit
    0.39
    🔘
    0.39
     existentes
    0.38
    蒇
    0.37
    POSITIVE LOGITS
     false
    0.42
     reagent
    0.39
     nat
    0.37
    ඳ
    0.37
    phony
    0.35
     indignation
    0.35
    釉
    0.35
     al
    0.35
     tamp
    0.34
    রায়
    0.34
    Activations Density 0.000%

    No Known Activations