© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199573
    Prev
    Next
    INDEX
    Explanations

    sorting by scores or values

    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_15_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
    :],
    0.52
    しくは
    0.50
     Çünkü
    0.49
     grö
    0.49
     굉장히
    0.49
     ال
    0.48
    ема
    0.48
     präsent
    0.47
    jande
    0.47
    awie
    0.46
    POSITIVE LOGITS
    un
    0.57
    us
    0.54
    N
    0.52
    成
    0.50
    uc
    0.50
    ois
    0.47
    します
    0.47
    ud
    0.46
    ach
    0.46
    name
    0.46
    Activations Density 0.001%

    No Known Activations