© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3108
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_5_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
    ྱི་
    3.62
    ்களை
    3.13
    ਹੀ
    2.58
    anks
    2.46
     curiosity
    2.37
     willing
    2.24
    መሳሳይ
    2.24
    ္
    2.24
    ்க
    2.21
    ین
    2.21
    POSITIVE LOGITS
     rispond
    2.70
    Leffler
    2.64
    种
    2.62
    Ре
    2.44
     ∣
    2.44
     Fälle
    2.41
    ੍ਹ
    2.38
     piace
    2.34
    下图
    2.31
     rhinophores
    2.31
    Activations Density 0.048%

    No Known Activations