© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65564
    Prev
    Next
    INDEX
    Explanations

    G

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     Bever
    0.43
    अप्र
    0.43
    َر
    0.43
     Ala
    0.41
     tsp
    0.41
    tsp
    0.41
     uni
    0.39
    𝒕
    0.39
     Rico
    0.38
     Toc
    0.38
    POSITIVE LOGITS
    omed
    0.43
    enz
    0.41
    мад
    0.40
    হাট
    0.40
     মত
    0.39
     шта
    0.38
    мель
    0.38
    DA
    0.38
    hemat
    0.38
    MZ
    0.38
    Activations Density 0.007%

    No Known Activations