© 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. 6269
    Prev
    Next
    INDEX
    Explanations

    stand by

    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
     Alltag
    2.01
    𝐞
    2.00
     zog
    1.96
    𝐯
    1.95
    ✠
    1.94
     tahu
    1.91
     eens
    1.89
    हाल
    1.89
     teniendo
    1.84
    まま
    1.82
    POSITIVE LOGITS
     adsorbed
    2.10
    ング
    2.01
    ointment
    1.96
     SafeArea
    1.96
    लों
    1.91
    м
    1.88
    chaoxing
    1.84
    லத்தில்
    1.77
    ைட்
    1.73
    to
    1.72
    Activations Density 0.020%

    No Known Activations