© 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. 5344
    Prev
    Next
    INDEX
    Explanations

    sys followed by project or folder

    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
    容
    0.37
     leak
    0.35
    olon
    0.35
     leaks
    0.35
    oload
    0.34
     काळ
    0.34
     outfits
    0.33
    TLS
    0.33
    iót
    0.33
     redis
    0.33
    POSITIVE LOGITS
     Antennes
    0.41
     poseen
    0.38
    牠
    0.37
     ब्राउन
    0.37
    upol
    0.36
     apresentam
    0.36
     ब्यू
    0.36
     possuem
    0.36
    raise
    0.35
    answered
    0.35
    Activations Density 0.024%

    No Known Activations