© 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. 3724
    Prev
    Next
    INDEX
    Explanations

    git conflict markers

    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
     nara
    1.63
     сві
    1.60
     sacchar
    1.54
    ゲ
    1.51
     koko
    1.50
    ста
    1.49
    স্ট
    1.48
     inextric
    1.47
    რი
    1.46
     изменить
    1.44
    POSITIVE LOGITS
    k
    1.70
    höhe
    1.49
    n
    1.48
     detach
    1.47
    ları
    1.46
    亼
    1.45
    ların
    1.44
     stries
    1.42
    rol
    1.42
    न
    1.41
    Activations Density 0.000%

    No Known Activations