© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88226
    Prev
    Next
    INDEX
    Explanations

    Clean Water Acts and India Mission

    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_3_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
    in
    0.86
    uv
    0.63
    ك
    0.63
    ла
    0.62
     Actualmente
    0.61
    ль
    0.58
    غ
    0.57
     claros
    0.55
    িম
    0.55
    σε
    0.55
    POSITIVE LOGITS
     l
    0.79
    PLAY
    0.79
    ST
    0.77
    KEEP
    0.74
    It
    0.70
    á
    0.70
     materialize
    0.66
    人
    0.66
     It
    0.66
    PS
    0.65
    Activations Density 0.002%

    No Known Activations