© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121145
    Prev
    Next
    INDEX
    Explanations

    statistics and critical values

    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_27_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
     Axios
    0.31
    धियों
    0.29
     виде
    0.29
    反应
    0.28
     зон
    0.28
     گزار
    0.28
     commons
    0.28
    敨
    0.28
    язку
    0.28
     Reed
    0.27
    POSITIVE LOGITS
    antro
    0.30
    small
    0.30
    AnyCPU
    0.30
     médicaments
    0.30
     mutant
    0.29
    ighty
    0.29
     curv
    0.29
    icar
    0.29
    abo
    0.29
    اسو
    0.29
    Activations Density 0.005%

    No Known Activations