© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6079
    Prev
    Next
    INDEX
    Explanations

    political skills and ability to legislate

    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_39_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
    为人
    0.39
    ▍
    0.38
     upheld
    0.37
    riya
    0.35
    ⤷
    0.35
     lj
    0.35
    ✊
    0.35
    ეგ
    0.34
    Additionally
    0.34
    ignan
    0.34
    POSITIVE LOGITS
     Valt
    0.47
     atmosph
    0.45
     invoc
    0.44
    messaging
    0.43
     altitudes
    0.41
    acetic
    0.41
     médi
    0.41
    CTest
    0.40
     GOP
    0.40
     elixir
    0.40
    Activations Density 0.057%

    No Known Activations