© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10080
    Prev
    Next
    INDEX
    Explanations

    align-items: center

    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_13_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
     shoe
    0.56
     kunna
    0.54
     memas
    0.52
     popped
    0.52
    ilai
    0.52
     sådan
    0.51
     &
    0.51
     didn
    0.51
     wel
    0.51
    ュー
    0.50
    POSITIVE LOGITS
    baseUrl
    0.58
    N
    0.57
     시간
    0.53
    แ
    0.52
    Cache
    0.52
    confusion
    0.52
    เวลา
    0.50
    ARN
    0.50
    Propagation
    0.50
    ™
    0.50
    Activations Density 0.004%

    No Known Activations