© 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. 140828
    Prev
    Next
    INDEX
    Explanations

    extra dimensions

    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
    AM
    0.26
    지
    0.24
    log
    0.24
    am
    0.24
    wei
    0.24
    utton
    0.24
    nova
    0.23
     simili
    0.23
    ping
    0.23
     kitchenette
    0.23
    POSITIVE LOGITS
    том
    0.23
     Star
    0.22
     harassing
    0.20
     nurturing
    0.20
     Seeking
    0.19
    ண
    0.19
     Grâce
    0.19
    ...\...\...\...\
    0.19
    的东西
    0.19
    的故事
    0.19
    Activations Density 0.001%

    No Known Activations