© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203180
    Prev
    Next
    INDEX
    Explanations

    flower shops and markets

    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_12_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
     Еще
    0.58
    at
    0.55
     повече
    0.52
    0.52
    oszt
    0.50
     Redistributions
    0.50
    작
    0.50
    쥔
    0.49
    ár
    0.49
     boute
    0.49
    POSITIVE LOGITS
     leisure
    0.60
     gospel
    0.58
     tourism
    0.53
     ethnic
    0.53
    Financial
    0.53
     america
    0.52
     minerals
    0.52
     social
    0.51
     racial
    0.51
     holistic
    0.51
    Activations Density 0.003%

    No Known Activations