© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3701
    Prev
    Next
    INDEX
    Explanations

    bbc news

    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
    м
    1.14
    en
    0.88
    info
    0.85
    master
    0.84
    ages
    0.81
    ap
    0.80
    man
    0.77
    my
    0.77
    ch
    0.76
    is
    0.76
    POSITIVE LOGITS
    Ⴚ
    0.95
    Ⴝ
    0.95
     connecté
    0.94
     functor
    0.94
     Bxa
    0.91
     ма
    0.90
    鋃
    0.88
     enviable
    0.88
     スカート
    0.87
    스러운
    0.87
    Activations Density 0.001%

    No Known Activations