© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51486
    Prev
    Next
    INDEX
    Explanations

    return or exceptions

    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_10_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
     enough
    0.53
     detection
    0.52
     iar
    0.49
     ყველ
    0.48
    9
    0.48
     a
    0.48
     raining
    0.48
     अ
    0.48
     acetic
    0.48
     ainsi
    0.47
    POSITIVE LOGITS
    hf
    0.49
    远处
    0.46
    '])){
    0.45
    ું
    0.45
     конца
    0.42
    ാര
    0.42
     hogares
    0.42
    ])){
    0.41
     Té
    0.40
     relaciones
    0.40
    Activations Density 0.000%

    No Known Activations