© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43661
    Prev
    Next
    INDEX
    Explanations

    random sampling

    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
    o
    0.77
    P
    0.75
     in
    0.75
    S
    0.74
    on
    0.73
    R
    0.71
    </h2>
    0.70
    ot
    0.69
    F
    0.68
    ide
    0.68
    POSITIVE LOGITS
    ות
    0.71
     трудно
    0.67
    עות
    0.63
     controle
    0.63
     haya
    0.62
     CVE
    0.61
     wist
    0.61
    веден
    0.61
     exag
    0.60
     override
    0.59
    Activations Density 0.003%

    No Known Activations