© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106034
    Prev
    Next
    INDEX
    Explanations

    automobiles and related industry

    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_1_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
    д
    1.18
    తో
    1.13
    R
    1.12
    ا
    1.09
    ב
    1.09
    اً
    1.06
    H
    1.06
    व
    1.06
    ו
    1.05
    S
    1.05
    POSITIVE LOGITS
    ist
    0.97
    us
    0.94
    arin
    0.93
    <0xA1>
    0.88
    ak
    0.86
     тексту
    0.86
    yn
    0.85
    é
    0.84
    ari
    0.83
     u
    0.82
    Activations Density 0.000%

    No Known Activations