© 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. 3170
    Prev
    Next
    INDEX
    Explanations

    generating ideas

    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
     Trong
    0.49
     pe
    0.47
     Lab
    0.46
     Bangladesh
    0.46
     Admir
    0.46
     admiration
    0.45
    ㅌ
    0.44
     Sodium
    0.44
     Iran
    0.44
     сві
    0.44
    POSITIVE LOGITS
    Starburst
    0.55
    ங்கிணை
    0.54
     dịp
    0.53
    рующие
    0.53
    ু
    0.52
    Modulo
    0.52
    tions
    0.52
    습니다
    0.52
     pinched
    0.51
    akn
    0.51
    Activations Density 0.002%

    No Known Activations