© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36162
    Prev
    Next
    INDEX
    Explanations

    etc

    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_50_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
    ũ
    0.38
    దాయ
    0.38
    ूव
    0.36
    mare
    0.36
     ======
    0.35
    ဧ
    0.35
     ------
    0.35
    বাংলার
    0.35
    槍
    0.34
     Fenn
    0.34
    POSITIVE LOGITS
    eting
    1.23
    etted
    1.11
    ets
    1.09
    eted
    1.09
    ETA
    1.06
    ETING
    1.05
    eter
    1.05
    eta
    1.02
    eters
    1.02
    ete
    1.02
    Activations Density 0.037%

    No Known Activations