© 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. 58207
    Prev
    Next
    INDEX
    Explanations

    describing something

    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
    :\
    0.63
    $.
    0.60
    :
    0.57
    o
    0.55
     perempt
    0.54
    Deletion
    0.54
    ():
    0.54
    ;\
    0.54
     preceded
    0.54
     eos
    0.53
    POSITIVE LOGITS
    RIO
    0.57
    šan
    0.53
     rocker
    0.48
     cholest
    0.47
    קים
    0.46
    如果不
    0.46
    र्तन
    0.46
    ឿង
    0.46
     isim
    0.46
     anhyd
    0.46
    Activations Density 0.001%

    No Known Activations