© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14258
    Prev
    Next
    INDEX
    Explanations

    Putin, North Korea, Ukraine

    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_15_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
     軍
    0.42
     சித்தர்
    0.39
     ឬ
    0.38
    Ⴊ
    0.37
    <unused415>
    0.36
    龺
    0.36
    酺
    0.36
    !।
    0.36
     सैन्य
    0.36
    ႃႇ
    0.36
    POSITIVE LOGITS
    <h2>
    0.39
     utter
    0.38
    ong
    0.33
    H
    0.32
    Ut
    0.32
    0.31
     sight
    0.30
     ibu
    0.30
    صح
    0.30
    হ
    0.30
    Activations Density 0.010%

    No Known Activations