© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6965
    Prev
    Next
    INDEX
    Explanations

    IRA or Iraq

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ット
    3.53
    ร์
    2.96
    й
    2.81
    তে
    2.58
    ار
    2.42
    ן
    2.41
     overwhelming
    2.37
    ২৩
    2.35
    ং
    2.34
    ছে
    2.31
    POSITIVE LOGITS
    correcto
    3.02
    er
    3.02
     buscan
    2.81
     μπορού
    2.76
    ي
    2.66
    ل
    2.62
    িতে
    2.55
     Vive
    2.50
     стара
    2.49
     simp
    2.45
    Activations Density 0.014%

    No Known Activations