© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205362
    Prev
    Next
    INDEX
    Explanations

    suggesting or implying

    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
    Mis
    0.40
    rants
    0.37
    Zeneca
    0.36
    stances
    0.36
    ophytic
    0.36
    mis
    0.35
    %%%%%%%%%%%%%
    0.35
     مرت
    0.34
    ⣤
    0.34
    osomes
    0.34
    POSITIVE LOGITS
     expected
    0.42
     Expected
    0.40
     aver
    0.37
     tid
    0.34
    expected
    0.34
    خن
    0.34
     Esper
    0.33
     Asociación
    0.33
     okay
    0.33
    Expected
    0.33
    Activations Density 0.003%

    No Known Activations