© 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. 42298
    Prev
    Next
    INDEX
    Explanations

    Makemake, Makalu

    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
    но
    1.00
     неё
    0.71
    ↵
    0.71
    ною
    0.67
    ні
    0.64
    ної
    0.64
     realized
    0.63
    ।’’
    0.63
    )।
    0.63
     cui
    0.62
    POSITIVE LOGITS
    h
    0.89
    ir
    0.86
     It
    0.85
    ha
    0.82
    annya
    0.73
    ப
    0.73
     일
    0.73
    have
    0.73
    It
    0.72
    pr
    0.71
    Activations Density 0.000%

    No Known Activations