© 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
    2. Gemma-3-4B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-16K
    4. 54
    Prev
    Next
    INDEX
    Explanations

    phrases that describe quantities or sizes.

    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
     Alberta
    0.11
    ينة
    0.11
     క
    0.11
    biotics
    0.11
     பொருள்
    0.10
     other
    0.10
     inf
    0.10
     知
    0.10
     در
    0.10
     therefore
    0.10
    POSITIVE LOGITS
    Chuck
    0.13
     unix
    0.11
    ()/
    0.11
    Asking
    0.11
    Nab
    0.11
    Service
    0.11
    Nad
    0.11
    Nucle
    0.11
    Flow
    0.11
     താഴ
    0.11
    Activations Density 4.083%

    No Known Activations