© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36982
    Prev
    Next
    INDEX
    Explanations

    Rüdiger, Dunning-Kruger, Rutger

    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
    ur
    0.71
    ರುವ
    0.68
    ן
    0.67
     Chambre
    0.66
    ни
    0.65
     Orthodox
    0.62
     Initializes
    0.61
     Offensive
    0.61
     Deportivo
    0.59
    지
    0.59
    POSITIVE LOGITS
    .
    0.91
    .。
    0.79
    .³
    0.72
    。「
    0.64
     (
    0.64
     (<
    0.63
    .#
    0.63
    .!
    0.62
     você
    0.61
     limbs
    0.60
    Activations Density 0.001%

    No Known Activations