© 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. 8599
    Prev
    Next
    INDEX
    Explanations

    current directory

    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
    ات
    1.18
    ность
    1.10
    ۔
    1.09
    ją
    1.03
    ά
    1.01
    ত্ব
    1.01
    ical
    0.98
    immersive
    0.97
    सेवी
    0.96
     Admittedly
    0.93
    POSITIVE LOGITS
    fälle
    1.16
    קט
    1.12
    ^{*}$
    1.06
    fica
    1.05
     ক্ষেত্রে
    1.04
    mektedir
    1.03
    aş
    1.03
     задачи
    1.01
    phenoxymethyl
    1.00
    ল
    1.00
    Activations Density 0.024%

    No Known Activations