© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199606
    Prev
    Next
    INDEX
    Explanations

    Let

    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_46_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
    ্টি
    0.40
    萍
    0.40
    bel
    0.38
    )^{*
    0.37
    raya
    0.37
    matical
    0.37
    Ny
    0.36
    様
    0.36
    FindingsRequest
    0.36
    ły
    0.36
    POSITIVE LOGITS
     siblings
    0.45
     وقف
    0.42
     korral
    0.39
     arrêter
    0.38
     Known
    0.38
     Twelve
    0.38
     Load
    0.38
     Problems
    0.38
     Translated
    0.38
     cult
    0.37
    Activations Density 0.001%

    No Known Activations