© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13780
    Prev
    Next
    INDEX
    Explanations

    hotel names and related information

    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_13_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
    นิ
    0.52
     Lithium
    0.50
     Authorities
    0.48
    openList
    0.48
    __))
    0.46
    ファ
    0.46
     lithium
    0.46
     obesidad
    0.46
    クロ
    0.45
    Authorities
    0.45
    POSITIVE LOGITS
    ών
    0.48
     dubbio
    0.47
     чыга
    0.46
    wirkung
    0.46
     કરવા
    0.45
    ಹಾರ
    0.45
    =-
    0.45
    થી
    0.44
    wght
    0.44
    itled
    0.43
    Activations Density 0.002%

    No Known Activations