© 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. 171459
    Prev
    Next
    INDEX
    Explanations

    tuple: containing

    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
     anything
    0.44
    XT
    0.41
     moan
    0.39
    razier
    0.39
     transverse
    0.39
    ֑
    0.39
     below
    0.39
     suck
    0.39
     mortals
    0.38
     laterally
    0.38
    POSITIVE LOGITS
    ལ
    0.46
    腖
    0.46
     educación
    0.45
     Students
    0.44
    乌
    0.43
     입
    0.43
     уто
    0.42
     hason
    0.42
     öğrenc
    0.41
    azione
    0.41
    Activations Density 0.001%

    No Known Activations