© 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. 49195
    Prev
    Next
    INDEX
    Explanations

    end of the day

    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
    '
    0.83
    leq
    0.73
     hadden
    0.65
    ָ
    0.64
    na
    0.63
     zeg
    0.61
    <0x84>
    0.61
    scaping
    0.61
    els
    0.59
    <0xA9>
    0.58
    POSITIVE LOGITS
    ق
    0.75
     days
    0.73
     encontr
    0.73
     electronic
    0.72
     unimaginable
    0.72
     acetone
    0.70
     consensual
    0.70
     inaccessible
    0.69
     antise
    0.67
     encourages
    0.66
    Activations Density 0.001%

    No Known Activations