© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174786
    Prev
    Next
    INDEX
    Explanations

    file path components

    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_24_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     عام
    0.44
     gestion
    0.41
    reden
    0.40
     الإ
    0.39
     fie
    0.38
    aisesti
    0.38
    </body>
    0.38
     Fig
    0.38
    intas
    0.37
    2
    0.37
    POSITIVE LOGITS
    থানি
    0.40
    úscula
    0.39
     módulos
    0.38
     contiennent
    0.37
    ヨーク
    0.36
    [multimodal]
    0.36
     coupes
    0.36
    𝐦
    0.35
     conjoint
    0.35
     نمونه
    0.35
    Activations Density 0.001%

    No Known Activations