© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76945
    Prev
    Next
    INDEX
    Explanations

    benefits and development

    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_31_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
     Electro
    0.41
     Jerry
    0.38
     Cur
    0.37
     Bourbon
    0.37
     swag
    0.37
     Elektr
    0.37
     handouts
    0.37
    电
    0.37
     electro
    0.36
    িস্ট
    0.36
    POSITIVE LOGITS
     talent
    0.46
     талант
    0.46
     talents
    0.42
     wasted
    0.40
    Waste
    0.39
     गं
    0.38
    maxY
    0.38
     talento
    0.38
     talented
    0.37
     wastage
    0.37
    Activations Density 0.045%

    No Known Activations