© 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. 52787
    Prev
    Next
    INDEX
    Explanations

    organization awards and youth 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
     فایل
    0.46
    аст
    0.44
    ༦
    0.39
    Capricorn
    0.38
    aterData
    0.38
    ющимся
    0.37
    ود
    0.37
    ፥
    0.37
    
    0.36
    Arrival
    0.36
    POSITIVE LOGITS
     giving
    0.46
     secretary
    0.46
     celebrated
    0.44
     provided
    0.42
     title
    0.42
     made
    0.41
     grand
    0.40
     bold
    0.40
     celebration
    0.39
     just
    0.39
    Activations Density 0.003%

    No Known Activations