© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136621
    Prev
    Next
    INDEX
    Explanations

    older versions / software

    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_12_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
     начинает
    0.47
     Saúde
    0.45
     Bình
    0.44
     vitamine
    0.44
    した
    0.43
    。</
    0.43
     maw
    0.43
    ያንዳንዱ
    0.42
    。\
    0.42
    ാനി
    0.42
    POSITIVE LOGITS
     jeopard
    0.53
    kke
    0.52
    плю
    0.48
    S
    0.48
     obso
    0.48
    δο
    0.47
     iza
    0.47
    daughter
    0.46
    receptor
    0.46
    جه
    0.46
    Activations Density 0.007%

    No Known Activations