Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3847
    Prev
    Next
    INDEX
    Explanations

    a bit followed by complexity

    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
    f
    1.03
    ك
    1.01
    backs
    0.97
     retrograde
    0.94
    greeting
    0.94
    ுகிறது
    0.92
     whatsoever
    0.92
    வற்றை
    0.92
    ೆಯ
    0.91
     _,
    0.90
    POSITIVE LOGITS
    খানি
    1.01
     forego
    0.91
     sonra
    0.89
     cus
    0.89
     Recreation
    0.86
     bit
    0.85
     luke
    0.84
     fiance
    0.84
    је
    0.84
     देर
    0.84
    Activations Density 0.078%

    No Known Activations