© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147429
    Prev
    Next
    INDEX
    Explanations

    organs, conditions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    increases
    0.43
     Chayin
    0.41
    Incre
    0.40
    inclusion
    0.40
     ዓይ
    0.38
    always
    0.37
     grinning
    0.37
    '])]
    0.37
     приобрета
    0.37
     Increases
    0.37
    POSITIVE LOGITS
    甚至
    0.40
     quali
    0.40
    тента
    0.36
     organ
    0.36
    易
    0.36
     even
    0.34
     QUAL
    0.34
     in
    0.34
    орга
    0.33
    quali
    0.33
    Activations Density 0.003%

    No Known Activations