© 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. 197319
    Prev
    Next
    INDEX
    Explanations

    URL components and surrounding code

    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
    '
    1.03
    h
    0.83
    es
    0.76
    al
    0.64
    ek
    0.60
    aching
    0.59
     κά
    0.59
     गीत
    0.58
    '...
    0.58
     कीट
    0.57
    POSITIVE LOGITS
    ר
    0.85
    Э
    0.77
    Я
    0.72
    Ş
    0.72
    C
    0.71
    値
    0.71
     gerade
    0.69
    E
    0.68
    أ
    0.68
    Е
    0.67
    Activations Density 0.000%

    No Known Activations