© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5533
    Prev
    Next
    INDEX
    Explanations

    medical and financial terms

    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
    er
    3.09
    ার
    3.08
    र
    2.82
    い
    2.68
    м
    2.58
    an
    2.26
    ‍♂️
    2.25
     مؤرشف
    2.19
    н
    2.17
    anées
    2.15
    POSITIVE LOGITS
    وت
    2.13
    im
    2.05
     aparecer
    2.01
    iduría
    2.01
     presa
    2.00
    णिज्य
    1.95
    oon
    1.93
     dotyczą
    1.90
    Doctors
    1.86
    სი
    1.84
    Activations Density 0.012%

    No Known Activations