© 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. 225923
    Prev
    Next
    INDEX
    Explanations

    vanilla, ordinary, plain

    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
    ed
    0.79
    al
    0.76
    ing
    0.73
    f
    0.70
    у
    0.67
    િ
    0.66
    v
    0.64
    n
    0.63
    ע
    0.63
    <0xAC>
    0.62
    POSITIVE LOGITS
    ção
    0.75
     schönsten
    0.72
    랑
    0.69
    0
    0.66
    đen
    0.63
    chem
    0.63
    리
    0.62
    ਰ
    0.61
    란
    0.61
    cija
    0.60
    Activations Density 0.001%

    No Known Activations