© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203793
    Prev
    Next
    INDEX
    Explanations

    structured text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    iex
    0.44
    ies
    0.39
    喉
    0.38
     завтра
    0.37
    ում
    0.37
     రే
    0.35
    ließlich
    0.35
    寥
    0.34
    ใจ
    0.34
    吸收
    0.34
    POSITIVE LOGITS
     ап
    0.44
     оби
    0.42
     apki
    0.41
     kenn
    0.40
    Beauty
    0.39
     табле
    0.37
    🍔
    0.37
     fringes
    0.36
     मामूली
    0.36
    Ellen
    0.36
    Activations Density 0.000%

    No Known Activations