© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212347
    Prev
    Next
    INDEX
    Explanations

    gratification

    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_5_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
    ,
    1.39
    ्स
    1.16
    1
    1.09
    ,.
    1.05
    า
    1.05
    ம்
    1.05
    ,【
    1.02
    n
    1.02
    ם
    1.02
    ,&
    1.02
    POSITIVE LOGITS
    ب
    1.19
    jší
    1.15
     concili
    1.13
    ر
    1.05
     liber
    1.02
     recommandée
    1.02
    ción
    0.99
     materialized
    0.99
    。【
    0.98
    рта
    0.98
    Activations Density 0.000%

    No Known Activations