© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11770
    Prev
    Next
    INDEX
    Explanations

    docker-compose or pinescript code blocks

    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_40_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
     Loose
    0.38
    ንድ
    0.38
     coughing
    0.38
     appointment
    0.38
    -(
    0.37
    接受
    0.36
    йо
    0.36
    getParameter
    0.36
     loose
    0.36
    כנס
    0.36
    POSITIVE LOGITS
     metallic
    0.39
    حدة
    0.39
     Beatty
    0.38
     organiques
    0.38
     arquivo
    0.36
     VIS
    0.36
    ipelago
    0.36
     정부
    0.36
    >}</
    0.36
    pperware
    0.36
    Activations Density 0.001%

    No Known Activations