© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3267
    Prev
    Next
    INDEX
    Explanations

    math and programming structures

    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_5_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
    ন
    0.21
    ड
    0.21
    ter
    0.21
    d
    0.21
    oretically
    0.20
    т
    0.20
     какая
    0.20
    ु
    0.20
    嘩
    0.19
    ere
    0.19
    POSITIVE LOGITS
     sina
    0.18
    tellers
    0.18
     pistol
    0.18
     chords
    0.18
     সম্প্র
    0.17
     strangers
    0.17
    ق
    0.17
    swire
    0.17
     Representatives
    0.17
    সন্ত
    0.17
    Activations Density 0.579%

    No Known Activations