© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 0
    Prev
    Next
    INDEX
    Explanations

    words related to academic or scholarly writing.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @ruq2026
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_12_width_16k_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
     eröffnet
    0.47
     toolPath
    0.45
     weltweit
    0.45
    謂
    0.43
     irgendwo
    0.42
    HasStarred
    0.41
    ുപത്രി
    0.41
     মুক্তিফ
    0.41
     allgemein
    0.41
     fenomen
    0.40
    POSITIVE LOGITS
     Only
    0.52
    ↵↵
    0.50
     These
    0.45
    Only
    0.44
     only
    0.43
     ONLY
    0.42
     Those
    0.42
     Never
    0.41
     Unless
    0.40
    Those
    0.38
    Activations Density 0.077%

    No Known Activations