© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98029
    Prev
    Next
    INDEX
    Explanations

    non-blocking I/O and operations

    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_14_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
     células
    0.51
     lesión
    0.49
     cellules
    0.48
    細胞
    0.46
    োলন
    0.44
    錐
    0.43
    会社
    0.43
     compañía
    0.43
     proteínas
    0.42
     пато
    0.42
    POSITIVE LOGITS
     होणार
    0.50
    C
    0.48
     Scanner
    0.48
     читать
    0.48
    органи
    0.47
     gange
    0.47
    aksi
    0.46
    s
    0.45
     ​​
    0.44
    ubah
    0.44
    Activations Density 0.037%

    No Known Activations