© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4787
    Prev
    Next
    INDEX
    Explanations

    `go run` commands

    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
    煕
    0.48
    焘
    0.45
     রপ্ত
    0.44
    երը
    0.43
    甾
    0.43
    thapi
    0.42
    遊び
    0.41
     rejoined
    0.41
    ヤ
    0.41
     objectionable
    0.41
    POSITIVE LOGITS
     pessoas
    0.88
     aparelho
    0.85
     Conselho
    0.84
     desconto
    0.81
     não
    0.80
     pessoa
    0.80
     Jardim
    0.80
     qualquer
    0.80
     Senhor
    0.80
     Igreja
    0.79
    Activations Density 0.003%

    No Known Activations