© 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. 10454
    Prev
    Next
    INDEX
    Explanations

    brown and cream colors

    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
    N
    0.37
    გრ
    0.35
    Nas
    0.34
    Z
    0.33
    year
    0.33
    Russian
    0.33
    Nash
    0.33
    Vertex
    0.33
    times
    0.32
    şehir
    0.32
    POSITIVE LOGITS
     коричне
    0.40
     Propaganda
    0.38
    ución
    0.38
    𝙤
    0.37
    ो
    0.36
     probabilmente
    0.35
     fawn
    0.35
    ا
    0.34
     CaCl
    0.34
     brownish
    0.33
    Activations Density 0.061%

    No Known Activations