© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43838
    Prev
    Next
    INDEX
    Explanations

    letter, ONE, three, i, earth

    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_22_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
     Tro
    0.15
     Ago
    0.14
     अभाव
    0.14
    ච
    0.14
     increased
    0.14
     tro
    0.14
     unbiased
    0.13
    рган
    0.13
     cah
    0.13
    صبحت
    0.13
    POSITIVE LOGITS
     rougeâtres
    0.15
     अधीनस्थों
    0.15
    ⺆
    0.14
    ระหว่าง
    0.14
    ędzynarod
    0.14
     പിന്നീ
    0.14
     Underwater
    0.14
     रियर
    0.14
    耷
    0.14
    നും
    0.13
    Activations Density 0.001%

    No Known Activations