© 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. 199745
    Prev
    Next
    INDEX
    Explanations

    IT

    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
    ท์
    0.48
    тів
    0.48
    트를
    0.46
    트에
    0.45
    ﺕ
    0.43
    thead
    0.42
    ttt
    0.42
    ৈর
    0.40
    ্টের
    0.40
    тах
    0.39
    POSITIVE LOGITS
    <0x8A>
    0.61
     IT
    0.55
    IT
    0.55
     ITV
    0.53
    आईटी
    0.48
    ИТ
    0.46
    itetty
    0.44
    િત
    0.43
    itelja
    0.43
    kitt
    0.42
    Activations Density 0.002%

    No Known Activations