© 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. 97444
    Prev
    Next
    INDEX
    Explanations

    metal, mechanical, or smooth

    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
    arsa
    0.58
    mi
    0.55
    name
    0.54
    اتی
    0.54
    اسی
    0.50
    저
    0.50
    ati
    0.50
    olid
    0.50
    ای
    0.49
    یر
    0.49
    POSITIVE LOGITS
    𝙛
    0.57
     danach
    0.56
     '\\;'
    0.56
     devra
    0.54
     zou
    0.53
     равен
    0.53
     mezcl
    0.53
     देम
    0.53
     ৃ
    0.52
     linken
    0.52
    Activations Density 0.000%

    No Known Activations