© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33451
    Prev
    Next
    INDEX
    Explanations

    minus (-), minuses, Минусы

    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_7_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
    osomes
    1.00
    ون
    0.94
    calls
    0.91
    ה
    0.91
    چ
    0.91
    મ
    0.91
     endorsements
    0.90
    ação
    0.90
    도
    0.90
     externalities
    0.89
    POSITIVE LOGITS
    п
    0.95
    ia
    0.89
    ari
    0.83
     gé
    0.83
    ارع
    0.81
     palind
    0.80
     вра
    0.79
     la
    0.78
     r
    0.77
     house
    0.77
    Activations Density 0.000%

    No Known Activations