© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157106
    Prev
    Next
    INDEX
    Explanations

    do not

    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
    部门
    0.44
    rij
    0.43
    itlement
    0.41
     manz
    0.41
    崛
    0.39
    cri
    0.38
    iji
    0.38
    ႇ
    0.38
     kamen
    0.37
     انہوں
    0.37
    POSITIVE LOGITS
    XA
    0.52
    xa
    0.48
    ZA
    0.46
    azza
    0.43
    OA
    0.43
    න්ට
    0.43
    Axis
    0.42
    xA
    0.42
     Ir
    0.42
    axis
    0.40
    Activations Density 0.001%

    No Known Activations