© 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. 24826
    Prev
    Next
    INDEX
    Explanations

    thousand followed by unit or count

    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
    <0x93>
    0.67
    iş
    0.66
    ijske
    0.63
    }$
    0.63
    }°
    0.63
    iyê
    0.63
    ün
    0.63
     площа
    0.62
    У
    0.62
    <0xA1>
    0.61
    POSITIVE LOGITS
    0.83
    ם
    0.74
    ll
    0.73
    л
    0.72
    tl
    0.70
    ﻢ
    0.70
    sulf
    0.69
    time
    0.69
    tm
    0.67
    조
    0.66
    Activations Density 0.015%

    No Known Activations