© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117820
    Prev
    Next
    INDEX
    Explanations

    percentages of paper sections

    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
     desaparecer
    0.45
     desapar
    0.41
     Roh
    0.40
    into
    0.39
    ٨
    0.39
     diminu
    0.38
    number
    0.38
     disappears
    0.38
    ácio
    0.38
    ಿಸ್
    0.37
    POSITIVE LOGITS
    滘
    0.35
     imagery
    0.35
     جوړونکو
    0.35
     utili
    0.35
     settings
    0.34
     recycl
    0.34
     granulated
    0.34
    Phase
    0.34
     äuß
    0.34
     classifiers
    0.33
    Activations Density 0.002%

    No Known Activations