© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14579
    Prev
    Next
    INDEX
    Explanations

    stolen chemicals or data

    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_13_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
     creatures
    0.37
     związane
    0.33
     \
    0.32
     radiance
    0.31
     $
    0.31
     festival
    0.30
     '$
    0.30
    YN
    0.30
     commotion
    0.30
    }-
    0.29
    POSITIVE LOGITS
    ंग
    0.35
    ?
    0.35
     تهیه
    0.35
    ahead
    0.34
    هم
    0.34
     कर
    0.33
    ।”
    0.33
    ए
    0.33
    이며
    0.32
    ,”
    0.32
    Activations Density 0.057%

    No Known Activations