© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7619
    Prev
    Next
    INDEX
    Explanations

    design and conduct experiments

    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
     brighten
    0.38
    ຊີ
    0.37
    Mud
    0.37
     unite
    0.35
     gateways
    0.35
    䡓
    0.35
    Robust
    0.35
    思
    0.35
     disrupts
    0.35
    olve
    0.35
    POSITIVE LOGITS
     Conduct
    0.51
     conduct
    0.50
    Conduct
    0.49
     conducted
    0.49
     conducting
    0.48
    CONDUCT
    0.46
     CONDUCT
    0.45
     провести
    0.45
     conducts
    0.45
    Invest
    0.44
    Activations Density 0.001%

    No Known Activations