© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210081
    Prev
    Next
    INDEX
    Explanations

    types of systems and elements

    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
     niego
    0.44
     যাবে
    0.42
    סט
    0.38
     нього
    0.38
     genere
    0.37
    сти
    0.36
    🙊
    0.36
     niej
    0.36
    스트
    0.35
    弇
    0.35
    POSITIVE LOGITS
     Battlefield
    0.42
     डेटा
    0.41
    ebilirsiniz
    0.37
     особенно
    0.36
    a
    0.35
    vaccinated
    0.35
    Ин
    0.34
    pred
    0.34
    databinding
    0.34
    विल
    0.34
    Activations Density 0.000%

    No Known Activations