© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175816
    Prev
    Next
    INDEX
    Explanations

    marsupial

    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_20_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
    ቹ
    0.44
     undergraduate
    0.44
    keyValue
    0.44
     accusations
    0.41
    ቿ
    0.41
    fileExistsAtPath
    0.41
     searchValue
    0.40
     മഹാ
    0.40
    ताज
    0.40
    🛥
    0.40
    POSITIVE LOGITS
     (
    0.49
     сокра
    0.47
     A
    0.47
     :
    0.46
     А
    0.46
    А
    0.45
     Man
    0.45
     Brigitte
    0.44
     \
    0.44
    Fr
    0.44
    Activations Density 0.001%

    No Known Activations