© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206888
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_56_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
    𝗋
    0.36
    britannien
    0.35
    煊
    0.35
    škai
    0.34
    ামার
    0.34
    aging
    0.33
    baren
    0.33
    方法は
    0.33
     akun
    0.33
    ndon
    0.33
    POSITIVE LOGITS
     шесть
    0.43
     العاشر
    0.39
     Quatre
    0.37
     ६
    0.36
    SIX
    0.36
     السادس
    0.36
     sixth
    0.36
    iativa
    0.36
     ३
    0.36
     seventh
    0.35
    Activations Density 0.001%

    No Known Activations