© 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. 6802
    Prev
    Next
    INDEX
    Explanations

    code keywords and punctuation

    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
    𝘬
    0.32
     BatchNorm
    0.31
    s
    0.31
    minimize
    0.31
    %)
    0.31
    𝘳
    0.30
     "")
    0.30
    🦯
    0.30
    (',
    0.29
    ed
    0.29
    POSITIVE LOGITS
     aceasta
    0.38
    ्रिक
    0.38
     naka
    0.34
    ৯
    0.34
     tratar
    0.32
    فين
    0.32
    AT
    0.32
    ٹ
    0.32
    في
    0.31
    цам
    0.31
    Activations Density 0.035%

    No Known Activations