© 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. 3558
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    sono
    1.14
     домаћинствима
    1.14
    el
    1.13
    йи
    1.13
     আক্রান্ত
    1.11
    剷
    1.11
     tvar
    1.10
    牍
    1.08
    kari
    1.08
     huk
    1.08
    POSITIVE LOGITS
    Comparing
    1.22
     देखते
    1.17
    \|
    1.15
    \{
    1.14
     éventuellement
    1.13
    Defining
    1.12
    \|\
    1.11
    ان
    1.10
    in
    1.10
     Libraries
    1.10
    Activations Density 0.000%

    No Known Activations