© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65708
    Prev
    Next
    INDEX
    Explanations

    learning curve

    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_51_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
    ده
    0.97
    deh
    0.79
    DE
    0.77
    दे
    0.73
     ده
    0.73
    دة
    0.70
    데
    0.69
    де
    0.67
    dea
    0.65
    de
    0.62
    POSITIVE LOGITS
    can
    0.47
    gay
    0.46
    mez
    0.45
    make
    0.43
    tib
    0.43
    Tab
    0.42
     Kane
    0.41
     Cana
    0.41
    zim
    0.41
    곶
    0.41
    Activations Density 0.001%

    No Known Activations