© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36444
    Prev
    Next
    INDEX
    Explanations

    quotes

    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_31_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
    -...
    0.36
    āyaṇa
    0.35
    ⏤
    0.35
    .-\
    0.34
    {-\
    0.34
    deleteAll
    0.33
    ^{*
    0.33
    \{-\
    0.33
    $--
    0.33
    AttributedString
    0.33
    POSITIVE LOGITS
    }|^{
    0.36
     technik
    0.35
     वीरता
    0.35
     gestures
    0.35
     वेव्स
    0.35
    রী
    0.34
     सम्
    0.34
     rounded
    0.34
     owing
    0.34
     क्रमशः
    0.34
    Activations Density 0.000%

    No Known Activations