© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46726
    Prev
    Next
    INDEX
    Explanations

    "body" or "use" followed by ":" or "strict"

    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_3_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
    با
    0.73
    ile
    0.73
    이다
    0.65
    かつ
    0.63
    and
    0.60
    O
    0.59
    러
    0.59
    anas
    0.58
     aguda
    0.58
     sozial
    0.57
    POSITIVE LOGITS
    s
    1.02
    d
    0.96
    т
    0.90
    ت
    0.86
    is
    0.83
    g
    0.83
    тран
    0.80
    r
    0.79
    ية
    0.75
    سے
    0.73
    Activations Density 0.004%

    No Known Activations