© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58119
    Prev
    Next
    INDEX
    Explanations

    trying too hard

    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_11_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
    ња
    0.60
    EVEN
    0.56
    Corresponding
    0.56
    resel
    0.54
    Rect
    0.53
    ן
    0.52
    ညာ
    0.52
    financing
    0.51
     perspici
    0.51
    Ownership
    0.50
    POSITIVE LOGITS
     ingles
    0.68
    és
    0.66
     flasks
    0.63
    ę
    0.63
    д
    0.62
     avec
    0.60
    érg
    0.60
    ą
    0.59
     elegantes
    0.59
    з
    0.58
    Activations Density 0.001%

    No Known Activations