© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5655
    Prev
    Next
    INDEX
    Explanations

    conduction and conductors

    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
    त
    3.17
    いえ
    2.88
    ta
    2.76
    га
    2.71
    en
    2.69
    bouw
    2.58
    trunc
    2.57
    да
    2.50
    و
    2.45
    al
    2.44
    POSITIVE LOGITS
     gracious
    2.69
     facendo
    2.57
     ViewHolder
    2.51
    нда
    2.45
     pues
    2.42
    iostream
    2.39
    ാര്യ
    2.38
     rehearing
    2.38
     snippet
    2.36
     doch
    2.32
    Activations Density 0.023%

    No Known Activations