© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1857
    Prev
    Next
    INDEX
    Explanations

    latex \usepackage

    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_39_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
     summed
    0.48
     Marcin
    0.41
     पर्व
    0.40
    ruvic
    0.39
     suma
    0.38
     phosphorylated
    0.38
    忪
    0.38
    反射
    0.37
    Cuánt
    0.37
    㭐
    0.37
    POSITIVE LOGITS
     imagery
    0.45
    ImagePath
    0.41
    theme
    0.40
    Imagery
    0.38
    housing
    0.38
    pressure
    0.38
    image
    0.37
     イメージ
    0.37
     itinéraires
    0.36
    path
    0.36
    Activations Density 0.000%

    No Known Activations