© 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. 124000
    Prev
    Next
    INDEX
    Explanations

    compiling a list

    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
     prevenção
    0.43
    校长
    0.40
     outermost
    0.38
     yǒu
    0.37
    素质
    0.37
     uppermost
    0.36
     prevención
    0.36
    磯
    0.36
    嗔
    0.35
     castes
    0.35
    POSITIVE LOGITS
    選
    0.98
     선정
    0.94
     انتخاب
    0.91
    选
    0.91
     chọn
    0.85
     selection
    0.85
     selecting
    0.84
     selezion
    0.83
     seç
    0.82
    を選
    0.82
    Activations Density 0.003%

    No Known Activations