© 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. 205316
    Prev
    Next
    INDEX
    Explanations

    CAUTION

    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
    ৬
    0.70
    8
    0.69
    ā
    0.61
    ۸
    0.60
     ისინი
    0.60
    arı
    0.59
    nij
    0.59
    9
    0.59
    ९
    0.59
    ৩
    0.58
    POSITIVE LOGITS
     of
    0.67
    CTION
    0.62
    ש
    0.62
    다
    0.60
    of
    0.59
    하는
    0.56
    IT
    0.55
    ции
    0.55
    TF
    0.55
    л
    0.55
    Activations Density 0.000%

    No Known Activations