© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202590
    Prev
    Next
    INDEX
    Explanations

    notice of

    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_37_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
    Parad
    0.40
     contacting
    0.38
    憲
    0.37
    uzzy
    0.36
     interests
    0.36
    FAN
    0.36
     striking
    0.35
    fan
    0.35
    ".*:
    0.35
     परीक्षा
    0.34
    POSITIVE LOGITS
     plán
    0.42
     προβ
    0.39
     oscillate
    0.38
     aank
    0.38
     landlab
    0.37
    تمد
    0.37
     божомолдор
    0.37
     계획
    0.37
    selectedValue
    0.37
     جب
    0.36
    Activations Density 0.001%

    No Known Activations