© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5085
    Prev
    Next
    INDEX
    Explanations

    class definitions

    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
    larının
    2.16
    ları
    2.13
    larına
    2.01
    間の
    1.99
    ların
    1.92
    
    1.92
    sizeof
    1.89
    ため
    1.84
    p
    1.84
     bestimmt
    1.83
    POSITIVE LOGITS
    \{\
    2.11
    \{(
    1.98
    otros
    1.96
    hereafter
    1.63
    اء
    1.62
    ᴿ
    1.62
     ব্যপারে
    1.61
     Поскольку
    1.58
    ጊዜ
    1.57
    ointed
    1.57
    Activations Density 0.004%

    No Known Activations