© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80063
    Prev
    Next
    INDEX
    Explanations

    bootstrap css or sampling

    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
    ི་
    0.35
     Canvas
    0.35
    ंग्रे
    0.35
    िकुलम
    0.35
     ট্যাক
    0.35
    ']},
    0.34
     संभावनाएं
    0.34
     спра
    0.34
     പ്രത്യ
    0.34
    隸
    0.34
    POSITIVE LOGITS
     library
    0.41
     dated
    0.34
    wString
    0.33
    平成
    0.33
     software
    0.32
     swinging
    0.32
    designated
    0.32
     Lester
    0.32
    Спо
    0.32
    elliptic
    0.32
    Activations Density 0.001%

    No Known Activations