© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17246
    Prev
    Next
    INDEX
    Explanations

    locations of hotels and cities

    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_34_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
     Brick
    0.50
     bricks
    0.48
     кирпи
    0.46
     Tiles
    0.44
     pavers
    0.44
     brick
    0.43
     कहां
    0.43
    砖
    0.43
    Brick
    0.43
     Pal
    0.39
    POSITIVE LOGITS
    北大
    0.39
    启发
    0.38
    phon
    0.37
    landı
    0.37
    jammer
    0.37
    deload
    0.37
     சக்த
    0.36
     potenci
    0.36
     shut
    0.35
    TextInput
    0.35
    Activations Density 0.015%

    No Known Activations