© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126602
    Prev
    Next
    INDEX
    Explanations

    Gena Lee Nolin

    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
    T
    0.59
    č
    0.59
    ன்
    0.57
    دخ
    0.56
    O
    0.56
    اج
    0.54
    مد
    0.53
    底
    0.53
    १९
    0.52
    N
    0.51
    POSITIVE LOGITS
     с
    0.67
     breathes
    0.64
    la
    0.64
    ра
    0.63
    s
    0.61
    ы
    0.61
     питания
    0.60
     ")
    0.59
     оцени
    0.58
     cinese
    0.58
    Activations Density 0.000%

    No Known Activations