© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88094
    Prev
    Next
    INDEX
    Explanations

    too much

    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
     cont
    0.41
     干
    0.40
     confusing
    0.40
     confuse
    0.38
     upkeep
    0.38
    casting
    0.37
    cont
    0.37
     confuses
    0.37
     cond
    0.36
     참
    0.36
    POSITIVE LOGITS
    Além
    0.40
    oreet
    0.40
     Kamm
    0.39
    ariah
    0.39
     supprim
    0.38
    教练
    0.38
    गमेंट
    0.38
     Wich
    0.37
     উঠে
    0.37
    deleted
    0.37
    Activations Density 0.009%

    No Known Activations