© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141927
    Prev
    Next
    INDEX
    Explanations

    chapters or answers

    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
    gera
    0.36
     thước
    0.35
    ebar
    0.34
    ἷ
    0.34
    vede
    0.33
    alsa
    0.33
     لذ
    0.33
     topped
    0.32
    strange
    0.32
    pecial
    0.32
    POSITIVE LOGITS
     Jaw
    0.47
     chapter
    0.46
     Chapter
    0.45
     jawaban
    0.42
     answers
    0.42
     Answers
    0.41
    chapter
    0.41
    Jaw
    0.41
    🐊
    0.41
    Chapter
    0.39
    Activations Density 0.000%

    No Known Activations