© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10836
    Prev
    Next
    INDEX
    Explanations

    Happy Birthday

    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_40_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
     escritos
    0.37
     regimes
    0.34
    蛻
    0.34
    TIA
    0.34
    峥
    0.34
     appré
    0.34
     régimen
    0.34
    意義
    0.33
     précie
    0.33
     appreciated
    0.33
    POSITIVE LOGITS
    는지
    0.38
    濑
    0.38
    கிர
    0.37
    க்கிர
    0.36
    ೯
    0.36
    ଠ
    0.35
    枓
    0.35
     Cri
    0.35
    bukti
    0.34
    Cri
    0.34
    Activations Density 0.008%

    No Known Activations