© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78629
    Prev
    Next
    INDEX
    Explanations

    date formatting

    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_53_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
     السي
    0.49
     си
    0.48
     سي
    0.43
    سي
    0.41
    석
    0.41
     simple
    0.38
     Sé
    0.38
     FR
    0.38
     ул
    0.38
    си
    0.37
    POSITIVE LOGITS
    愕
    0.43
    Greg
    0.40
    agma
    0.39
     wz
    0.39
    DbContext
    0.39
    वते
    0.39
    Wr
    0.39
    ioon
    0.38
     Lalu
    0.37
     dlr
    0.37
    Activations Density 0.000%

    No Known Activations