© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258427
    Prev
    Next
    INDEX
    Explanations

    headers =

    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_22_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
     நன்கு
    0.41
     जोग
    0.38
     أف
    0.38
    ឈ្មោះ
    0.38
     ய
    0.38
     fotografías
    0.38
     प्रॉप
    0.38
    पतवार
    0.38
     গুগল
    0.38
    pidos
    0.38
    POSITIVE LOGITS
    Calc
    0.42
     ends
    0.40
     нашей
    0.40
    める
    0.40
    End
    0.39
    It
    0.39
     Malaria
    0.39
    (
    0.38
    Secondly
    0.38
    Alberta
    0.38
    Activations Density 0.001%

    No Known Activations