© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18129
    Prev
    Next
    INDEX
    Explanations

    GPT-4

    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_34_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
    etes
    0.28
    㫻
    0.28
     puțin
    0.27
     العين
    0.27
    㬹
    0.27
     ભ
    0.27
    ancias
    0.27
    eces
    0.27
    𝐵
    0.27
    㽡
    0.27
    POSITIVE LOGITS
     policymakers
    0.32
     sorts
    0.29
     commodities
    0.28
     Palma
    0.28
     innovators
    0.27
     dashboards
    0.27
    vars
    0.27
    말로
    0.27
    ంత్రి
    0.26
     Commodities
    0.26
    Activations Density 0.062%

    No Known Activations