© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 259985
    Prev
    Next
    INDEX
    Explanations

    childhood trauma experiences

    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_10_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
    ꯡ
    0.34
     -------------
    0.32
     తగ్
    0.31
    %%%%%%%%%%%%%%%%
    0.31
    methylene
    0.30
     sintomas
    0.30
    
    0.30
    ඖ
    0.29
     στη
    0.29
    opies
    0.28
    POSITIVE LOGITS
    Hero
    0.34
     héros
    0.34
     Hero
    0.34
     Heroes
    0.33
    Heroes
    0.32
     explo
    0.32
     maakte
    0.31
     exploited
    0.31
    ຄ
    0.31
     benefactor
    0.30
    Activations Density 0.002%

    No Known Activations