© 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. 42282
    Prev
    Next
    INDEX
    Explanations

    ad hoc networks

    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
    1
    0.75
     in
    0.68
    াভাব
    0.65
    iensis
    0.63
     kuni
    0.61
    3
    0.61
    ر
    0.60
     పాటు
    0.59
    드시
    0.59
    ta
    0.58
    POSITIVE LOGITS
    مس
    0.63
    ara
    0.62
    ang
    0.60
     OTHERWISE
    0.59
    á
    0.59
     spør
    0.58
    é
    0.58
    ire
    0.57
    行
    0.57
     BUILDING
    0.56
    Activations Density 0.002%

    No Known Activations