© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84570
    Prev
    Next
    INDEX
    Explanations

    use serde::Serialize

    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_23_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
     specs
    0.41
     apportion
    0.39
     médiocrement
    0.39
     rectilinear
    0.38
     divid
    0.38
    हरे
    0.38
     ρ
    0.38
     computerized
    0.38
    ですよ
    0.37
     proprietors
    0.37
    POSITIVE LOGITS
    佞
    0.41
     Echt
    0.39
     Miners
    0.39
    Hell
    0.38
     Hola
    0.38
     Św
    0.38
    训练
    0.38
     This
    0.38
    闪
    0.38
     Ниж
    0.37
    Activations Density 0.000%

    No Known Activations