© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150849
    Prev
    Next
    INDEX
    Explanations

    Minister or cm

    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_18_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
    mi
    0.33
    man
    0.33
    shi
    0.33
    map
    0.32
    क
    0.31
    men
    0.30
    link
    0.30
    hi
    0.29
    marker
    0.29
    p
    0.29
    POSITIVE LOGITS
     gleichen
    0.34
     গাড়
    0.32
     toutefois
    0.31
    ція
    0.31
     NEM
    0.30
    軚
    0.30
     tyre
    0.30
     ዓይነት
    0.30
     deinen
    0.30
     необхід
    0.29
    Activations Density 0.001%

    No Known Activations