© 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. 6628
    Prev
    Next
    INDEX
    Explanations

    finding an exact match

    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
    er
    2.38
    й
    2.38
    '"
    2.19
    ோ
    2.12
    ার
    2.01
    ways
    2.00
    ज
    1.99
    り
    1.97
    ان
    1.96
    ल्ल्या
    1.95
    POSITIVE LOGITS
     evidenced
    2.83
     functors
    2.64
     geodes
    2.50
    t
    2.35
     respeito
    2.33
     especializado
    2.32
     thymus
    2.32
    राधिक
    2.28
     mathbf
    2.21
    𝒕
    2.21
    Activations Density 0.003%

    No Known Activations