© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121393
    Prev
    Next
    INDEX
    Explanations

    dog"""

    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
    犬
    0.70
    Dog
    0.70
     dogs
    0.69
     Dog
    0.69
     dog
    0.67
     DOG
    0.64
     犬
    0.63
    Dogs
    0.60
    dogs
    0.58
     Dogs
    0.58
    POSITIVE LOGITS
     impacto
    0.40
    Sib
    0.39
     sib
    0.37
     glyph
    0.36
     impacted
    0.36
     ather
    0.35
    样式
    0.35
     borrar
    0.35
     stripping
    0.35
    𝐩
    0.35
    Activations Density 0.008%

    No Known Activations