© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181845
    Prev
    Next
    INDEX
    Explanations

    either... or

    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_29_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
     หรือ
    0.39
    或是
    0.38
    或者
    0.36
    或者是
    0.36
    หรือ
    0.35
    Nin
    0.34
     或者
    0.34
    或
    0.33
    하거나
    0.32
     অথবা
    0.32
    POSITIVE LOGITS
     adulti
    0.33
     всех
    0.32
    eleron
    0.32
    alá
    0.32
     entrambe
    0.32
     entrambi
    0.31
     Targets
    0.31
     pendientes
    0.31
    pov
    0.31
    钚
    0.31
    Activations Density 0.008%

    No Known Activations