© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110825
    Prev
    Next
    INDEX
    Explanations

    o, os, aron, nA

    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_2_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
    l
    1.02
    y
    0.90
    n
    0.89
    en
    0.78
    ۹
    0.76
    p
    0.73
    m
    0.73
    arse
    0.72
    ları
    0.71
    r
    0.71
    POSITIVE LOGITS
    0.98
    ка
    0.88
    ırd
    0.71
    <h4>
    0.68
     vineyards
    0.65
    ня
    0.65
     transistors
    0.65
     Львів
    0.64
    ્ર
    0.64
    يلي
    0.63
    Activations Density 0.000%

    No Known Activations