© 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. 4652
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and question words

    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
     scare
    0.63
    $.\\
    0.52
    婳
    0.52
    )\\
    0.51
     nums
    0.51
     ette
    0.50
    le
    0.50
     crawling
    0.49
     debunk
    0.49
    ially
    0.49
    POSITIVE LOGITS
    сколько
    0.63
    ਹ
    0.58
    centroid
    0.57
    詁
    0.56
     supplémentaire
    0.55
     laboratoire
    0.55
    zess
    0.55
     empate
    0.54
     birefringence
    0.54
    س
    0.54
    Activations Density 0.083%

    No Known Activations