© 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. 88272
    Prev
    Next
    INDEX
    Explanations

    SPECIALIZATION

    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
    စျေး
    0.49
    糁
    0.46
     συνεργ
    0.45
    ARIFF
    0.44
     وصول
    0.44
    क्रीम
    0.44
     सहयोग
    0.43
    цене
    0.42
    তত্ব
    0.41
    یاط
    0.41
    POSITIVE LOGITS
     P
    0.43
     '
    0.43
     ski
    0.41
     Ski
    0.41
     Bhan
    0.41
     Ser
    0.39
     BMW
    0.39
     B
    0.38
     K
    0.38
     Open
    0.38
    Activations Density 0.000%

    No Known Activations