© 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. 38867
    Prev
    Next
    INDEX
    Explanations

    positively followed by impact or change

    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
    い
    0.69
     Α
    0.68
     Quindi
    0.66
    א
    0.64
     ಅ
    0.64
     ア
    0.64
    ア
    0.62
     デ
    0.62
    ある
    0.61
     ა
    0.61
    POSITIVE LOGITS
    ters
    0.56
     bút
    0.56
    it
    0.55
    en
    0.55
     do
    0.53
     sympathetic
    0.52
     MDF
    0.52
    er
    0.51
    ")
    0.51
    ship
    0.51
    Activations Density 0.004%

    No Known Activations