© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101526
    Prev
    Next
    INDEX
    Explanations

    default_popup

    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_16_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
     r
    0.62
    der
    0.59
     ر
    0.58
    ter
    0.57
    ewater
    0.55
    ivali
    0.55
    water
    0.55
    unità
    0.54
    ar
    0.54
     Shayari
    0.54
    POSITIVE LOGITS
    我们会
    0.53
    တတ်
    0.50
    <0xAC>
    0.47
    жити
    0.47
    আমরা
    0.46
    ちなみに
    0.46
    మ్‌
    0.45
    温
    0.45
    逭
    0.45
    我们在
    0.44
    Activations Density 0.010%

    No Known Activations