© 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. 202947
    Prev
    Next
    INDEX
    Explanations

    birdwatching, treehouse building

    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
    표
    0.43
     obstruction
    0.39
    slope
    0.38
     fr
    0.37
     Pto
    0.35
     gen
    0.35
    Slope
    0.35
     Cal
    0.34
    夜
    0.34
     displaced
    0.34
    POSITIVE LOGITS
     hides
    0.61
     hide
    0.57
    Hide
    0.55
     blind
    0.54
     Hide
    0.53
     blinds
    0.52
     Blind
    0.47
     hiding
    0.47
    Blind
    0.46
     hid
    0.46
    Activations Density 0.011%

    No Known Activations