© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1521
    Prev
    Next
    INDEX
    Explanations

    JSON output labels

    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_39_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
     ridden
    0.38
     まし
    0.36
     shouted
    0.36
    試料
    0.35
     scarred
    0.35
    ↺
    0.35
    লাভ
    0.34
    ಂಕ
    0.34
    资料
    0.34
     পণ্ডিত
    0.34
    POSITIVE LOGITS
     Type
    0.37
     eins
    0.36
     confianza
    0.35
    ("@
    0.35
     Version
    0.34
    leşt
    0.34
    ("
    0.34
     vertrou
    0.34
     Συ
    0.33
     Description
    0.33
    Activations Density 0.066%

    No Known Activations