© 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. 3443
    Prev
    Next
    INDEX
    Explanations

    dependency despite

    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
    le
    1.70
    vati
    1.67
    watercolor
    1.67
     владе
    1.63
    NN
    1.60
    𝘴
    1.59
    𝘯
    1.54
    рити
    1.52
    पति
    1.45
    𝘥
    1.44
    POSITIVE LOGITS
     regard
    1.83
     względu
    1.81
     resorting
    1.63
     fail
    1.50
     disabilities
    1.43
    ,$$
    1.37
     Luckily
    1.36
     учета
    1.36
    för
    1.36
     accès
    1.34
    Activations Density 0.046%

    No Known Activations