© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14619
    Prev
    Next
    INDEX
    Explanations

    html, server components, manifest, stylesheet

    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
    eil
    0.39
    ডিং
    0.39
    liter
    0.38
     förb
    0.37
    뭉
    0.37
    φος
    0.37
    confidence
    0.37
     confidence
    0.37
    ফত
    0.37
     Confidence
    0.37
    POSITIVE LOGITS
     ಬ
    0.40
    пле
    0.38
     ਆਪਣ
    0.38
     MenuItem
    0.37
    pperm
    0.37
    ज़ाइन
    0.37
    Whilst
    0.36
    ivable
    0.36
    displaystyle
    0.35
    bc
    0.35
    Activations Density 0.017%

    No Known Activations