© 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. 57189
    Prev
    Next
    INDEX
    Explanations

    elaborate on any aspect

    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
    ین
    0.65
    ط
    0.63
    </strong>
    0.59
    Events
    0.59
    ід
    0.59
    MLB
    0.58
    Interface
    0.57
    v
    0.57
    ge
    0.57
    ashi
    0.56
    POSITIVE LOGITS
     flores
    0.70
     fluores
    0.65
     ans
    0.65
    ’
    0.63
     erken
    0.62
     armas
    0.62
     andro
    0.61
     tack
    0.60
     MALDI
    0.60
     aus
    0.59
    Activations Density 0.002%

    No Known Activations