© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148671
    Prev
    Next
    INDEX
    Explanations

    political career

    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_23_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
     پورا
    0.45
     प्लेइंग
    0.43
     OZ
    0.43
     sold
    0.42
     shipped
    0.42
     pravo
    0.42
     sketches
    0.41
     [(
    0.39
    rott
    0.39
     आतंकी
    0.39
    POSITIVE LOGITS
     apprentices
    0.39
    年齢
    0.37
    ჲ
    0.37
    ização
    0.36
     Apprentices
    0.35
     индиви
    0.35
    ロール
    0.34
    igment
    0.34
    yloxy
    0.33
     జన్
    0.33
    Activations Density 0.001%

    No Known Activations