© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6105
    Prev
    Next
    INDEX
    Explanations

    debugger and compile settings

    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_39_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
     contoured
    0.43
     stell
    0.43
     dusted
    0.42
     விரி
    0.40
     prisms
    0.40
    醯
    0.40
     Lenz
    0.39
    तरीय
    0.39
    setChecked
    0.39
     চমৎকার
    0.38
    POSITIVE LOGITS
     Рим
    0.40
     Функ
    0.39
     որ
    0.38
    은행
    0.37
    ikte
    0.37
    Start
    0.37
     Zach
    0.37
     Munch
    0.36
     희
    0.36
    BANK
    0.36
    Activations Density 0.000%

    No Known Activations