© 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. 137324
    Prev
    Next
    INDEX
    Explanations

    Amazon SageMaker

    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
     puch
    0.44
     Comparison
    0.40
    Comparison
    0.39
    comparison
    0.39
     AFFA
    0.39
    chette
    0.39
    擲
    0.38
    陞
    0.37
     comparison
    0.37
    គ្រឿង
    0.37
    POSITIVE LOGITS
    Ed
    0.38
    ecido
    0.38
     Ey
    0.37
    jpg
    0.37
     Marcus
    0.35
     Vy
    0.34
     απε
    0.34
    argmax
    0.34
     clue
    0.34
    目光
    0.34
    Activations Density 0.001%

    No Known Activations