© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44150
    Prev
    Next
    INDEX
    Explanations

    reporting, self-reporting

    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_3_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
    u
    0.64
    ྰ
    0.61
    ro
    0.59
    ote
    0.57
    ía
    0.55
    <0xEE>
    0.55
    ી
    0.55
    ");
    0.54
     requisito
    0.54
     strictest
    0.54
    POSITIVE LOGITS
    د
    0.90
                                
    0.71
    im
    0.69
    𝚔
    0.68
    arası
    0.68
    d
    0.65
    ل
    0.65
    organizations
    0.63
                                 
    0.62
     își
    0.62
    Activations Density 0.000%

    No Known Activations