© 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. 162400
    Prev
    Next
    INDEX
    Explanations

    key concepts and principles

    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
    indications
    0.44
    parameters
    0.42
     two
    0.42
     இரண்டு
    0.42
     ც
    0.42
    ریشن
    0.41
     drei
    0.40
     دو
    0.38
     zwei
    0.38
     وهنا
    0.38
    POSITIVE LOGITS
    \"",
    0.36
     appro
    0.35
    챕
    0.35
     주로
    0.34
     Least
    0.34
    ほぼ
    0.34
    NAMEN
    0.34
    ವರ್
    0.33
    zip
    0.33
     explorer
    0.33
    Activations Density 0.012%

    No Known Activations