© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53268
    Prev
    Next
    INDEX
    Explanations

    understand how to use

    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_31_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
    loans
    0.37
    <unused10>
    0.36
    ơn
    0.35
    াহার
    0.34
    โอ
    0.34
     reschedule
    0.34
    sav
    0.34
    脹
    0.34
    വന
    0.34
     thérapeutique
    0.34
    POSITIVE LOGITS
    IAC
    0.37
    に対応
    0.34
     prisms
    0.34
     dut
    0.33
    鷗
    0.33
    prism
    0.33
    ঘট
    0.32
    您的
    0.32
    CY
    0.32
    Formal
    0.32
    Activations Density 0.014%

    No Known Activations