© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7017
    Prev
    Next
    INDEX
    Explanations

    java, jar, jndi, api, jxplorer, jython

    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_39_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
     Obviously
    0.32
    峋
    0.31
    resu
    0.30
     outrageous
    0.30
     खैर
    0.30
    BLY
    0.29
    平凡
    0.28
     TECHNIQUES
    0.28
    ならば
    0.28
     техники
    0.28
    POSITIVE LOGITS
    jav
    0.33
     jars
    0.31
    jar
    0.30
     jar
    0.30
     port
    0.30
    瓜
    0.30
    jam
    0.29
     jav
    0.29
    ją
    0.29
    sourceforge
    0.29
    Activations Density 0.007%

    No Known Activations