© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84919
    Prev
    Next
    INDEX
    Explanations

    blu-ray or dvd

    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_23_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
    予約
    0.40
     ตอน
    0.39
    enario
    0.38
    pathy
    0.38
     respuesta
    0.37
    Խ
    0.37
    เสื้อ
    0.36
     Honey
    0.35
     कॉफी
    0.35
     magazines
    0.35
    POSITIVE LOGITS
    फ्ते
    0.41
     ugljik
    0.40
    vertebr
    0.39
    穣
    0.39
    ocese
    0.38
     occidentale
    0.38
    thickness
    0.38
     vertebr
    0.38
     fatten
    0.38
    nemidophorus
    0.38
    Activations Density 0.000%

    No Known Activations