© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152807
    Prev
    Next
    INDEX
    Explanations

    manifest, info, Dictionary

    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_23_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
    鵜
    0.43
     pairs
    0.41
     ي
    0.40
    quem
    0.40
     पटक
    0.38
     пере
    0.37
     ä
    0.37
     assicur
    0.36
     asegur
    0.36
     πρόσ
    0.36
    POSITIVE LOGITS
     resultMap
    0.42
    部分
    0.41
    osoma
    0.40
    )(=
    0.39
     Smith
    0.38
    等等
    0.38
    ላለ
    0.38
     террито
    0.37
    وضوع
    0.37
    Smith
    0.37
    Activations Density 0.000%

    No Known Activations