© 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. 35413
    Prev
    Next
    INDEX
    Explanations

    set

    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
    स्तान
    0.42
    gha
    0.40
    ົາ
    0.39
    墻
    0.38
    usely
    0.37
    味的
    0.37
    hyde
    0.36
    infiltration
    0.36
     gxh
    0.35
    gador
    0.35
    POSITIVE LOGITS
    <tbody>
    0.44
    []
    0.38
     Be
    0.38
     topik
    0.37
     Bernoulli
    0.37
     berb
    0.36
     Definitely
    0.36
    蹩
    0.36
    erness
    0.36
    铌
    0.36
    Activations Density 0.001%

    No Known Activations