© 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. 167617
    Prev
    Next
    INDEX
    Explanations

    his policies

    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
    ellular
    0.40
    terms
    0.38
    MART
    0.38
    癥
    0.37
    terraform
    0.36
    WA
    0.35
    CA
    0.35
    Bill
    0.34
     leth
    0.34
     stampa
    0.34
    POSITIVE LOGITS
    ⇧
    0.37
     প্রতিনিধিত্ব
    0.36
     प्रतिनिधित्व
    0.36
     шы
    0.36
     മല
    0.34
     storing
    0.34
     കത്തി
    0.34
    随时
    0.34
     напротив
    0.34
    ρω
    0.33
    Activations Density 0.002%

    No Known Activations