© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80867
    Prev
    Next
    INDEX
    Explanations

    pie related concepts

    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_0_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
    د
    1.80
    д
    1.72
     and
    1.70
    م
    1.66
    ग
    1.62
    ز
    1.59
    ض
    1.49
    س
    1.48
    ل
    1.44
    та
    1.41
    POSITIVE LOGITS
    ية
    1.90
     a
    1.34
    kenalkan
    1.24
    вает
    1.22
    ла
    1.20
    naire
    1.16
    arak
    1.13
     εται
    1.13
    ানুভূতি
    1.09
    sembling
    1.08
    Activations Density 0.001%

    No Known Activations