© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 4817
    Prev
    Next
    INDEX
    Explanations

    -centric wards

    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
    о
    1.49
    ين
    1.45
    􀂾
    1.44
    \(
    1.39
    িং
    1.37
    speople
    1.36
    
    1.35
    и
    1.33
    ಳ್ಳಿ
    1.30
    国
    1.30
    POSITIVE LOGITS
    ities
    1.41
     Justiça
    1.33
    ها
    1.32
    ிறது
    1.26
    ரள
    1.21
     kè
    1.20
     verdade
    1.20
     এছাড়াও
    1.19
    erweise
    1.15
    <bos>
    1.14
    Activations Density 0.033%

    No Known Activations