© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210497
    Prev
    Next
    INDEX
    Explanations

    maps into

    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_20_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
    *
    0.46
     Chan
    0.44
    жа
    0.42
     Ві
    0.41
     Н
    0.41
    包括
    0.41
    нет
    0.41
     איך
    0.40
    担
    0.40
    ▶
    0.40
    POSITIVE LOGITS
     manifesting
    0.46
     conclusiones
    0.46
     skilful
    0.44
     ప్రభు
    0.44
     yazı
    0.43
     manifiesta
    0.43
     respectivas
    0.43
     কর্তা
    0.43
     maest
    0.43
     സര്‍
    0.43
    Activations Density 0.000%

    No Known Activations