© 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. 5691
    Prev
    Next
    INDEX
    Explanations

    fault, defect, bugs

    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
     tròn
    2.20
     герой
    2.18
    و
    2.01
    ाल
    1.95
    arity
    1.94
    ḗ
    1.93
    uine
    1.92
     damned
    1.92
    Translatef
    1.92
     lopen
    1.89
    POSITIVE LOGITS
    م
    2.78
    ve
    2.41
    된
    2.40
    р
    2.39
    き
    2.27
    𝓃
    2.24
    ició
    2.22
    িতে
    2.20
    ch
    2.17
    viel
    2.17
    Activations Density 0.118%

    No Known Activations