© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141211
    Prev
    Next
    INDEX
    Explanations

    Event Functions

    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_12_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
     designates
    0.58
     rows
    0.50
     scouts
    0.48
    လ
    0.46
     seraient
    0.46
    нету
    0.46
     interes
    0.46
    "।
    0.45
     тө
    0.45
     상품
    0.45
    POSITIVE LOGITS
    ches
    0.61
    rimiento
    0.56
     enforce
    0.54
    aires
    0.53
    chers
    0.52
    riminate
    0.52
    }}}}$
    0.51
     разными
    0.51
    ations
    0.50
    зирован
    0.50
    Activations Density 0.004%

    No Known Activations