© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206010
    Prev
    Next
    INDEX
    Explanations

    ethnic armed conflict

    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_20_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
    量
    0.34
     Nab
    0.33
     nab
    0.32
     Z
    0.31
     Kurt
    0.31
     Group
    0.30
     Tab
    0.30
    க
    0.30
     Schn
    0.30
    áp
    0.30
    POSITIVE LOGITS
     jornada
    0.33
     alianza
    0.32
    的日子
    0.31
    ⟦
    0.31
    ⊃
    0.31
     নির্বাচ
    0.30
     chão
    0.30
     தேசிய
    0.30
    ঞ্চলের
    0.30
    ឧ
    0.30
    Activations Density 0.001%

    No Known Activations