© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194139
    Prev
    Next
    INDEX
    Explanations

    public service loan forgiveness

    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_15_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
     thermocouple
    0.59
     啊
    0.52
     pesky
    0.52
    ந்துள்ளது
    0.51
     chloroplast
    0.50
     sawdust
    0.50
     haven
    0.50
     oceanic
    0.50
    厂
    0.50
     ámbito
    0.49
    POSITIVE LOGITS
            
    0.62
    mood
    0.58
    m
    0.56
    me
    0.56
    atoare
    0.56
    end
    0.55
    ม
    0.55
    ्रीम
    0.54
    م
    0.54
     Aquare
    0.54
    Activations Density 0.001%

    No Known Activations