© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39679
    Prev
    Next
    INDEX
    Explanations

    code control flow

    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_11_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
     dumpling
    0.60
     m
    0.57
     pathname
    0.57
     mL
    0.56
     factorial
    0.56
     jim
    0.56
     miscellaneous
    0.55
     transitive
    0.55
     tumor
    0.55
     gui
    0.55
    POSITIVE LOGITS
    o
    0.63
    ienia
    0.61
    clientsdetails
    0.59
    ług
    0.58
    ка
    0.57
     בז
    0.57
    літы
    0.57
    Czy
    0.56
    Argb
    0.56
    Hasil
    0.56
    Activations Density 0.076%

    No Known Activations