© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1859
    Prev
    Next
    INDEX
    Explanations

    Swedish politics and immigration

    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_40_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
    plac
    0.37
    ົາ
    0.36
    sinx
    0.36
    दय
    0.36
     port
    0.35
     proven
    0.35
    캔
    0.35
    وش
    0.35
     empl
    0.34
    EQ
    0.34
    POSITIVE LOGITS
    כר
    0.51
     Zoho
    0.37
    ัญ
    0.36
    োয়া
    0.35
    ibban
    0.34
    পর্য
    0.34
    ২০
    0.34
    ^{-}\
    0.34
     Wirtschaft
    0.34
    嗬
    0.34
    Activations Density 0.008%

    No Known Activations