© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203686
    Prev
    Next
    INDEX
    Explanations

    presented by

    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_6_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
    обходимо
    0.98
    ת
    0.94
    ר
    0.90
     ángulo
    0.88
    ل
    0.88
    ก
    0.88
    ый
    0.88
    其他
    0.87
     ocasion
    0.86
     duplicating
    0.85
    POSITIVE LOGITS
    da
    1.24
    na
    1.22
    ga
    1.09
    kal
    1.06
    di
    1.05
    og
    1.03
    ue
    1.03
    de
    1.03
    den
    1.02
    je
    0.98
    Activations Density 0.000%

    No Known Activations