© 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. 91419
    Prev
    Next
    INDEX
    Explanations

    furnishings and furniture

    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
    ва
    0.71
    রা
    0.67
    са
    0.67
    ก
    0.63
     aprend
    0.59
    сти
    0.59
     consapevole
    0.58
     importante
    0.57
     migliore
    0.56
    ड़ा
    0.55
    POSITIVE LOGITS
    AY
    0.75
    dü
    0.65
    IL
    0.65
    liert
    0.60
    IR
    0.57
    寐
    0.57
    IP
    0.55
    itektur
    0.55
    ayar
    0.55
    Jy
    0.55
    Activations Density 0.001%

    No Known Activations