© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17764
    Prev
    Next
    INDEX
    Explanations

    masonry and mason jars

    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_40_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
    чей
    0.41
     cál
    0.38
    వల
    0.35
    㖅
    0.35
     clases
    0.35
     rä
    0.34
    ället
    0.33
    刦
    0.33
    Extract
    0.32
     hoja
    0.32
    POSITIVE LOGITS
     konfigur
    0.40
     DAB
    0.38
    configuration
    0.38
     Conservative
    0.38
    improvement
    0.38
    ব্রি
    0.37
    Conservative
    0.37
    භාව
    0.37
     configuration
    0.36
    ក្រ
    0.36
    Activations Density 0.000%

    No Known Activations