© 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. 61816
    Prev
    Next
    INDEX
    Explanations

    yield and wait for seconds

    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
    elt
    0.52
    eth
    0.52
    eds
    0.50
    "],
    0.50
    ees
    0.49
     સ્વ
    0.49
    </span>
    0.48
     balle
    0.48
    ehir
    0.47
    eta
    0.47
    POSITIVE LOGITS
     Connections
    0.54
    новним
    0.54
     Roasted
    0.52
    姏
    0.51
    VICIO
    0.50
     IMPRO
    0.50
     Wrapped
    0.50
    都有
    0.49
    лович
    0.49
     perlu
    0.49
    Activations Density 0.002%

    No Known Activations