© 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. 140721
    Prev
    Next
    INDEX
    Explanations

    coriander or peeled ingredients

    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
     n
    0.61
    ekten
    0.55
     dangers
    0.49
     selfies
    0.48
    erkt
    0.48
     arrests
    0.47
     tulips
    0.46
    시간
    0.46
     nationalists
    0.46
    န်
    0.45
    POSITIVE LOGITS
    表演
    0.63
    Healthcare
    0.57
    Which
    0.56
    Barcelona
    0.55
    <code>
    0.54
    Example
    0.54
    Basketball
    0.53
     Which
    0.53
     Angebot
    0.53
     Accounting
    0.52
    Activations Density 0.005%

    No Known Activations