© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26396
    Prev
    Next
    INDEX
    Explanations

    gaps around things

    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
    v
    1.06
    p
    0.86
    of
    0.76
     as
    0.75
    ti
    0.73
     time
    0.72
    time
    0.72
    pm
    0.72
    other
    0.71
    ä
    0.70
    POSITIVE LOGITS
     presenceData
    0.78
     waarvan
    0.76
     dí
    0.75
     biais
    0.73
     dangereux
    0.73
     setToDefault
    0.71
     لأ
    0.71
     apresenta
    0.70
     합니다
    0.70
     principalTable
    0.70
    Activations Density 0.003%

    No Known Activations