© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152240
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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_23_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
    dyž
    0.45
    ▣
    0.43
    academic
    0.43
                            
    0.42
    দি
    0.41
    োদ্ধ
    0.41
     pudding
    0.40
     budete
    0.40
     enormes
    0.40
    правления
    0.40
    POSITIVE LOGITS
    ACTIVE
    0.41
     ủng
    0.39
    同比
    0.38
     използ
    0.37
    ATIV
    0.37
     गणित
    0.36
     }}(\
    0.36
     bán
    0.35
     dữ
    0.35
     zarówno
    0.35
    Activations Density 0.010%

    No Known Activations