© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91016
    Prev
    Next
    INDEX
    Explanations

    only

    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
    글
    0.60
     to
    0.59
    TextUtils
    0.54
    -
    0.53
    an
    0.52
     (
    0.51
    lessly
    0.50
    lessness
    0.50
    els
    0.50
    less
    0.50
    POSITIVE LOGITS
     unbelievably
    0.55
     Coinbase
    0.55
     Shivaji
    0.55
     barges
    0.55
     правом
    0.54
     impeded
    0.53
    f
    0.53
     interruptions
    0.52
     okazji
    0.52
     meinem
    0.52
    Activations Density 0.001%

    No Known Activations