© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24521
    Prev
    Next
    INDEX
    Explanations

    detailed answers

    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_56_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
     я
    0.71
     je
    0.54
     y
    0.46
     YA
    0.45
     ya
    0.45
    Я
    0.45
     야
    0.44
     jag
    0.44
     يا
    0.44
    ヤ
    0.41
    POSITIVE LOGITS
    ซ
    0.54
     par
    0.52
     Hr
    0.47
     Ethnicity
    0.47
    hr
    0.44
    ours
    0.43
     hr
    0.43
     Un
    0.43
     finishes
    0.42
    our
    0.42
    Activations Density 0.003%

    No Known Activations