© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85001
    Prev
    Next
    INDEX
    Explanations

    fractions involving roots and powers

    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_23_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
    jas
    0.40
    河南
    0.40
     क्षेत्रा
    0.40
    Satellite
    0.39
    panels
    0.38
    ployed
    0.37
    شون
    0.37
    ⿲
    0.37
    উল্লেখ্য
    0.37
    parency
    0.36
    POSITIVE LOGITS
     intermin
    0.46
     daqu
    0.42
     saludar
    0.41
     Girl
    0.39
     Sound
    0.39
     Pythagoras
    0.38
    醋
    0.38
     idő
    0.37
     posición
    0.36
     사랑
    0.36
    Activations Density 0.001%

    No Known Activations