© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51377
    Prev
    Next
    INDEX
    Explanations

    dark mode

    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_10_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
    I
    0.79
    A
    0.66
    5
    0.57
    1
    0.57
    O
    0.55
    H
    0.55
    T
    0.54
    Τ
    0.54
    AV
    0.52
    na
    0.52
    POSITIVE LOGITS
     dark
    0.85
     Dark
    0.79
     DARK
    0.77
     darker
    0.73
     darkness
    0.72
     oscura
    0.70
    Dark
    0.66
     oscuro
    0.66
     darkened
    0.64
     darkening
    0.64
    Activations Density 0.026%

    No Known Activations