© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86750
    Prev
    Next
    INDEX
    Explanations

    cumulus clouds or courriel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ת
    1.01
    y
    1.00
    т
    0.85
    ی
    0.80
    י
    0.79
    ت
    0.74
    ي
    0.71
    ն
    0.71
    м
    0.69
    त
    0.68
    POSITIVE LOGITS
    0
    0.94
    ’
    0.85
    '
    0.71
    ０
    0.66
    ongono
    0.64
     for
    0.62
    ৯
    0.62
    ﺮ
    0.60
    amed
    0.59
    ikt
    0.59
    Activations Density 0.001%

    No Known Activations