© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40453
    Prev
    Next
    INDEX
    Explanations

    mangrove forests restoration

    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_11_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
    9
    0.62
     musicals
    0.61
     incendio
    0.61
     নিঃসন্দে
    0.60
    通话
    0.59
    مر
    0.59
     máscara
    0.59
     intima
    0.58
     commodo
    0.57
     válv
    0.57
    POSITIVE LOGITS
     в
    0.62
     -
    0.54
    р
    0.54
     shrugged
    0.53
     протягом
    0.52
    ють
    0.52
    ва
    0.51
    sville
    0.50
    рьох
    0.50
     Chesapeake
    0.50
    Activations Density 0.005%

    No Known Activations