© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78806
    Prev
    Next
    INDEX
    Explanations

    coronation and swords

    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_0_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
    s
    1.63
    AN
    1.57
    m
    1.53
    IT
    1.50
    ↵
    1.46
     l
    1.45
    AL
    1.45
     is
    1.41
    RE
    1.41
     an
    1.35
    POSITIVE LOGITS
    larda
    1.84
    ין
    1.73
    مي
    1.68
    larni
    1.68
    ي
    1.67
    ться
    1.66
    lardan
    1.65
    د
    1.54
    י
    1.52
    lere
    1.45
    Activations Density 0.000%

    No Known Activations