© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134722
    Prev
    Next
    INDEX
    Explanations

    different types of

    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_6_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
    0.88
    t
    0.85
    ının
    0.83
    r
    0.75
    lilik
    0.75
    that
    0.73
    köz
    0.70
    ânt
    0.69
    arın
    0.68
    ก
    0.66
    POSITIVE LOGITS
     powied
    0.72
    ご利用
    0.66
    د
    0.66
    ご飯
    0.65
    وم
    0.64
    م
    0.64
    ق
    0.64
    ies
    0.63
    oc
    0.63
    ock
    0.63
    Activations Density 0.009%

    No Known Activations