© 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. 97215
    Prev
    Next
    INDEX
    Explanations

    optical element or sensor

    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
    ’,
    0.56
    见到
    0.53
     」,
    0.52
    」，
    0.52
    eneration
    0.52
     “,
    0.50
    visible
    0.49
    <0x0D>
    0.49
    ilte
    0.49
    су
    0.48
    POSITIVE LOGITS
     устройства
    0.59
     problèmes
    0.58
     ఏర్ప
    0.54
     PROBLEMS
    0.54
     problemas
    0.52
     triángulos
    0.52
    й
    0.52
     빠른
    0.51
     errores
    0.51
     ብቻ
    0.50
    Activations Density 0.001%

    No Known Activations