© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233806
    Prev
    Next
    INDEX
    Explanations

    model.evaluate

    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_32_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
     proximity
    0.44
     ahu
    0.43
     gamma
    0.39
     gần
    0.39
     kup
    0.39
     thiệt
    0.38
    槐
    0.37
     alarm
    0.36
     قریب
    0.35
     inaccurate
    0.35
    POSITIVE LOGITS
    urger
    0.38
    ListPage
    0.37
     CHO
    0.36
    要做
    0.36
    ={()=>
    0.36
     exploration
    0.35
    ര്‍ണ
    0.35
     રહ
    0.35
    不可以
    0.35
    arela
    0.35
    Activations Density 0.003%

    No Known Activations