© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31176
    Prev
    Next
    INDEX
    Explanations

    Check

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     bids
    0.33
     undertakings
    0.30
    stead
    0.30
    <0xE3>
    0.29
     programa
    0.29
     biodiesel
    0.29
     বিচারপতি
    0.29
    ੰ
    0.29
     genera
    0.28
     biodegradable
    0.28
    POSITIVE LOGITS
    yourself
    0.37
     LAV
    0.36
     запусти
    0.32
     பற்றிய
    0.31
     পিটার
    0.31
    ঠাকুর
    0.31
     traigo
    0.31
    BOUR
    0.31
     PYTHONPATH
    0.30
     설치
    0.30
    Activations Density 0.045%

    No Known Activations