© 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. 222890
    Prev
    Next
    INDEX
    Explanations

    matplotlib plotting functions

    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
    AND
    0.66
    هن
    0.63
     सड़क
    0.63
    MAKE
    0.62
    Don
    0.61
    BAR
    0.61
    ED
    0.61
    お
    0.60
    琬
    0.60
    FIX
    0.60
    POSITIVE LOGITS
    ją
    0.76
    azione
    0.75
    "،
    0.75
    angan
    0.75
     된
    0.75
    aza
    0.73
    ustration
    0.73
     하는
    0.73
    '',
    0.71
     gyven
    0.71
    Activations Density 0.005%

    No Known Activations