© 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. 124904
    Prev
    Next
    INDEX
    Explanations

    width= attribute

    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
    getSelected
    0.41
    CodeGen
    0.40
     Lock
    0.38
    ন্দরী
    0.37
    nění
    0.36
    iolipin
    0.36
     Ever
    0.35
    ရ
    0.35
    ەند
    0.35
     Ultr
    0.34
    POSITIVE LOGITS
     sizes
    0.47
    尺寸
    0.45
    WithSize
    0.45
     hossz
    0.45
     size
    0.45
     размере
    0.43
    Size
    0.42
     размеров
    0.42
     centimetres
    0.41
     etching
    0.41
    Activations Density 0.001%

    No Known Activations