© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199894
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

    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_50_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
     freed
    0.39
    Zi
    0.38
    志
    0.37
     Zi
    0.37
    ashe
    0.36
    ﺼ
    0.36
    জি
    0.35
     nutrition
    0.35
    滋
    0.35
     gratification
    0.35
    POSITIVE LOGITS
    کند
    0.41
    beiter
    0.39
    гин
    0.39
    ayo
    0.38
    ay
    0.36
    AY
    0.36
    bing
    0.36
    ായ
    0.36
    ایت
    0.36
    agin
    0.36
    Activations Density 0.003%

    No Known Activations