© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126898
    Prev
    Next
    INDEX
    Explanations

    ansible roles playbook script

    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_37_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
    甲方
    0.40
    管理
    0.40
    管理的
    0.38
     quản
    0.36
     strictly
    0.36
    amaz
    0.36
    教育
    0.36
    仃
    0.36
     管理
    0.36
    advertising
    0.35
    POSITIVE LOGITS
    Fireworks
    0.40
     horticultural
    0.38
     frameworks
    0.38
     shimmering
    0.37
     fluttering
    0.37
     peony
    0.36
     lining
    0.36
    वाज
    0.35
     pink
    0.35
     horse
    0.35
    Activations Density 0.001%

    No Known Activations