© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152701
    Prev
    Next
    INDEX
    Explanations

    double occupancy

    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
    ifu
    0.46
    脓
    0.41
     abi
    0.40
    浆
    0.40
    Shannon
    0.40
     ayak
    0.39
     leche
    0.38
    韦
    0.37
     ediyoruz
    0.36
     dant
    0.36
    POSITIVE LOGITS
     anyone
    0.42
     கிட்டத்தட்ட
    0.42
     consultants
    0.41
    建設
    0.41
     localización
    0.41
     Anyone
    0.40
     nearly
    0.40
    早已
    0.40
     Partners
    0.40
     cliché
    0.40
    Activations Density 0.000%

    No Known Activations