© 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. 3655
    Prev
    Next
    INDEX
    Explanations

    waste off insult be bother smooth just worry pretend

    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
     менее
    0.29
     advances
    0.27
     Disturb
    0.26
    ്ലാ
    0.26
    씌
    0.26
    有问题
    0.26
    害
    0.26
     inverted
    0.26
    衄
    0.26
     adanya
    0.26
    POSITIVE LOGITS
     ₽
    0.35
    ট
    0.34
    voll
    0.34
    ल
    0.33
    ⌐
    0.33
    Ε
    0.33
    ிறது
    0.32
     Ο
    0.32
    anjutan
    0.32
     collett
    0.32
    Activations Density 0.148%

    No Known Activations