© 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. 5746
    Prev
    Next
    INDEX
    Explanations

    Hindi, Korean, Japanese language identifiers

    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
    겐
    2.17
    tang
    2.12
    دار
    2.10
    ος
    2.06
    gay
    2.01
    -\
    1.98
    ला
    1.95
    ների
    1.88
     escorted
    1.85
    itarian
    1.84
    POSITIVE LOGITS
    ed
    2.26
    ة
    2.18
    ною
    1.96
    는
    1.91
    おそらく
    1.90
    atic
    1.86
    ro
    1.85
    ătur
    1.84
    能
    1.83
    م
    1.81
    Activations Density 0.007%

    No Known Activations