© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202802
    Prev
    Next
    INDEX
    Explanations

    prueba (try/test)

    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_6_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
    。
    1.75
    0
    1.52
    p
    1.07
    2
    1.07
    For
    1.04
     for
    1.02
    for
    1.00
    1
    0.98
     as
    0.98
    ول
    0.96
    POSITIVE LOGITS
    acción
    1.02
    ansı
    1.02
     one
    1.02
     conceivable
    1.00
    ۴
    1.00
    ியை
    0.97
     propulsion
    0.96
    ння
    0.95
     calving
    0.93
     уйнау
    0.93
    Activations Density 0.000%

    No Known Activations