© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38894
    Prev
    Next
    INDEX
    Explanations

    accumulate

    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_3_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
    ש
    0.76
    پ
    0.75
    ль
    0.71
    ll
    0.70
    พ
    0.68
    E
    0.67
    al
    0.66
    ਪ
    0.66
    score
    0.64
    sa
    0.63
    POSITIVE LOGITS
    ↵
    0.68
     knih
    0.67
    '
    0.66
    <0x86>
    0.61
    zinho
    0.60
     ideje
    0.59
     mág
    0.57
    <0x94>
    0.57
    يري
    0.57
     функції
    0.57
    Activations Density 0.001%

    No Known Activations