© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193703
    Prev
    Next
    INDEX
    Explanations

    buenas prácticas

    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_4_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
    <0x80>
    0.74
     المصفوفه
    0.70
     هیڅ
    0.68
     classificação
    0.67
     położ
    0.67
     culoare
    0.67
    ین
    0.66
    ное
    0.65
     thatched
    0.64
     ഒഴിവാ
    0.64
    POSITIVE LOGITS
    1
    0.82
    b
    0.82
    '
    0.73
     of
    0.72
    ps
    0.72
    3
    0.71
    kken
    0.71
     Itali
    0.70
    있
    0.70
    ١
    0.69
    Activations Density 0.000%

    No Known Activations