© 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. 29396
    Prev
    Next
    INDEX
    Explanations

    innocent, acquitted, or conviction

    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
    ів
    0.59
     nitride
    0.54
    t
    0.50
    𒅖
    0.50
    IZ
    0.49
    '?
    0.49
     posi
    0.49
     proinflammatory
    0.49
     api
    0.48
     prüfe
    0.48
    POSITIVE LOGITS
    5
    0.67
    6
    0.66
    3
    0.58
    ме
    0.57
    0
    0.57
    7
    0.57
    ح
    0.56
    at
    0.55
    ılar
    0.54
    4
    0.50
    Activations Density 0.012%

    No Known Activations