© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209866
    Prev
    Next
    INDEX
    Explanations

    from_pretrained

    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_20_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
    ']):
    0.49
     اُن
    0.49
     можна
    0.49
    CTE
    0.47
    RAJ
    0.46
     використовувати
    0.46
     کوئی
    0.45
    Ň
    0.45
    簱
    0.44
     gespeichert
    0.43
    POSITIVE LOGITS
     thickness
    0.54
     casing
    0.48
     ratio
    0.45
     crad
    0.44
     cu
    0.43
     tires
    0.43
     patches
    0.43
     sleepers
    0.43
     instar
    0.43
     offsets
    0.43
    Activations Density 0.001%

    No Known Activations