© 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. 14267
    Prev
    Next
    INDEX
    Explanations

    modern history and philosophy

    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
    ăți
    0.51
    ufig
    0.46
    ớp
    0.45
     finito
    0.45
     chụp
    0.45
     ಕಾ
    0.45
     blinded
    0.44
     퍼
    0.44
    foregroundView
    0.44
     ఉంట
    0.44
    POSITIVE LOGITS
     शही
    0.49
    s
    0.46
    ным
    0.45
    ের
    0.45
    ノ
    0.43
    ций
    0.43
    новых
    0.43
    sustaining
    0.43
    нови
    0.42
    0.42
    Activations Density 0.019%

    No Known Activations