© 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. 39466
    Prev
    Next
    INDEX
    Explanations

    watch brands and parts

    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
    ’
    0.55
    UP
    0.53
    </b>
    0.50
    osan
    0.49
    esta
    0.48
    심
    0.47
    id
    0.47
    ID
    0.47
     validar
    0.47
     visible
    0.47
    POSITIVE LOGITS
     Jacq
    0.51
    TimeDict
    0.50
     Forschung
    0.50
    coco
    0.50
     człowie
    0.50
     Nürnberg
    0.49
     klim
    0.48
    kirche
    0.48
     pessoa
    0.47
    tDBOutput
    0.47
    Activations Density 0.007%

    No Known Activations