© 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. 7072
    Prev
    Next
    INDEX
    Explanations

    within it

    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
    ل
    1.08
    ora
    1.02
    רות
    0.99
    이
    0.96
    ड़
    0.95
    tions
    0.94
    placed
    0.93
    ек
    0.91
    বন্ত
    0.91
    গন্ধ
    0.90
    POSITIVE LOGITS
    どり
    1.09
    ם
    1.08
    м
    1.07
     entsprechend
    1.07
     sopra
    1.06
     enige
    1.00
    ことができる
    0.99
     wszyst
    0.99
     eigenvalue
    0.96
     paternity
    0.95
    Activations Density 0.059%

    No Known Activations