© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34043
    Prev
    Next
    INDEX
    Explanations

    breakdown of

    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_3_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
    ,
    0.77
    i
    0.70
    ي
    0.68
    ి
    0.61
    โยชน์
    0.59
    ينا
    0.58
    íti
    0.58
     JPMorgan
    0.57
     fortiter
    0.55
    くらい
    0.54
    POSITIVE LOGITS
    c
    0.86
    S
    0.68
    V
    0.68
    dem
    0.67
    N
    0.67
    H
    0.67
    ró
    0.66
    های
    0.66
    dan
    0.64
    down
    0.63
    Activations Density 0.075%

    No Known Activations