© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141737
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to

    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_12_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
    sers
    0.50
     ಪ್ರಮಾಣ
    0.50
    spending
    0.48
    ця
    0.47
    啓
    0.47
    ફે
    0.46
    ౪
    0.45
    تد
    0.45
    ਲ
    0.45
    лі
    0.44
    POSITIVE LOGITS
     cuadrado
    0.60
     ocho
    0.60
     comando
    0.59
     Anschluss
    0.59
     encima
    0.58
     enfri
    0.58
     Kubrick
    0.58
     arquitectura
    0.57
     encerr
    0.57
     FROM
    0.57
    Activations Density 0.002%

    No Known Activations