© 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. 38937
    Prev
    Next
    INDEX
    Explanations

    login form page

    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
    س
    0.80
     for
    0.71
     descub
    0.68
    1
    0.67
     pertence
    0.65
     ajuda
    0.64
     fibroblasts
    0.64
    ی
    0.63
     quería
    0.63
     pertenece
    0.63
    POSITIVE LOGITS
    ad
    0.63
    ви
    0.60
     Passenger
    0.57
     Refugee
    0.57
    ма
    0.55
    楧
    0.54
     on
    0.53
    গ্রহায়ণ
    0.53
    il
    0.52
     Journal
    0.52
    Activations Density 0.007%

    No Known Activations