© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244468
    Prev
    Next
    INDEX
    Explanations

    python streamlit code

    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_40_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
     Theta
    0.41
    Drinks
    0.39
    Indeed
    0.38
    ##########
    0.37
    嫦
    0.37
     Indeed
    0.36
     cerr
    0.36
     Amen
    0.36
     drinks
    0.36
    Amen
    0.35
    POSITIVE LOGITS
     Lakes
    0.44
     /^
    0.43
     snapping
    0.40
     reacting
    0.39
    فيه
    0.38
     दंग
    0.38
    靚
    0.38
    孖
    0.37
     damping
    0.36
     rept
    0.36
    Activations Density 0.000%

    No Known Activations