© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222794
    Prev
    Next
    INDEX
    Explanations

    sooner or later

    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_10_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
    ك
    0.95
     goles
    0.86
     continuación
    0.80
     détermine
    0.76
     potência
    0.75
     limitaciones
    0.74
     consape
    0.74
     transformación
    0.73
     arenas
    0.73
     funzione
    0.73
    POSITIVE LOGITS
    v
    1.16
    h
    1.06
    se
    1.04
    en
    1.01
    r
    1.01
    t
    1.00
    w
    0.96
    oz
    0.94
    es
    0.93
    et
    0.93
    Activations Density 0.000%

    No Known Activations