© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242104
    Prev
    Next
    INDEX
    Explanations

    If you

    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
     refugees
    0.39
     раствор
    0.39
    naked
    0.39
    acceptable
    0.39
     calculado
    0.38
    ⊠
    0.38
     refugi
    0.37
     क्षतिग्रस्त
    0.37
     তাঁকে
    0.36
     ভীত
    0.36
    POSITIVE LOGITS
    舆
    0.41
     Cet
    0.39
     GDP
    0.37
     обращения
    0.36
     люби
    0.35
     Chip
    0.35
    ڌ
    0.35
    чити
    0.34
     adidas
    0.34
     Osc
    0.33
    Activations Density 0.008%

    No Known Activations