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. 4418
    Prev
    Next
    INDEX
    Explanations

    Mattermost, HHI, Rocket.Chat

    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
    й
    0.67
    ️⃣
    0.62
     rapp
    0.60
     phe
    0.58
     सोते
    0.57
     direccion
    0.57
     gratification
    0.56
    upcoming
    0.55
    חר
    0.55
    𝙞
    0.55
    POSITIVE LOGITS
    此之外
    0.75
    LE
    0.59
    də
    0.59
     право
    0.59
    आरआई
    0.58
    eted
    0.56
    inink
    0.56
     เอ่อ
    0.56
    தியை
    0.56
    jų
    0.56
    Activations Density 0.001%

    No Known Activations