© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171218
    Prev
    Next
    INDEX
    Explanations

    posting information online

    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_20_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
    Seperti
    0.31
     adverts
    0.29
    Turkey
    0.28
    ቤት
    0.28
     неба
    0.28
    🧉
    0.28
     variedad
    0.28
     iklan
    0.28
     dieron
    0.28
     distrito
    0.27
    POSITIVE LOGITS
     electromagnetic
    0.30
    closePath
    0.29
    pertension
    0.29
     गला
    0.29
    すぎ
    0.29
    }}+
    0.28
    sel
    0.27
    思路
    0.27
    过度
    0.27
     over
    0.27
    Activations Density 0.001%

    No Known Activations