© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7926
    Prev
    Next
    INDEX
    Explanations

    C# code structure

    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
     utterances
    2.43
    yf
    2.17
    owning
    2.15
    𝑉
    2.12
    turbine
    2.07
     Redemption
    2.04
     MNRAS
    2.03
    VOR
    2.02
    milliseconds
    2.02
     Treaty
    2.00
    POSITIVE LOGITS
    ন্যাশনাল
    2.19
    тся
    2.13
     fois
    2.06
    عرف
    2.05
    دور
    2.04
    د
    2.03
     pomocy
    2.01
    ியை
    1.94
    دام
    1.93
    なります
    1.89
    Activations Density 0.001%

    No Known Activations