© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209623
    Prev
    Next
    INDEX
    Explanations

    editing new draft content

    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
    ட்கள்
    0.30
     utilizzo
    0.27
    ita
    0.23
     تسجيل
    0.23
    unchecked
    0.23
    ṱ
    0.23
    ใส่
    0.23
     dentures
    0.23
     দক্ষিণে
    0.22
    true
    0.22
    POSITIVE LOGITS
    EMANN
    0.28
     Gemeinschaft
    0.26
    MANN
    0.24
    станови
    0.24
     tempore
    0.23
    倣
    0.23
    ahar
    0.23
     LaTeX
    0.23
    ocompat
    0.23
     forego
    0.23
    Activations Density 0.001%

    No Known Activations