© 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. 1
    Prev
    Next
    INDEX
    Explanations

    English words related to location.

    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
    ਟ
    0.24
    acchati
    0.20
    aparikkh
    0.20
    娯
    0.20
    राधना
    0.19
    匆
    0.19
    alahan
    0.19
    oting
    0.19
     routers
    0.19
    ⺠
    0.19
    POSITIVE LOGITS
    <unused2217>
    0.19
    ాము
    0.18
     Franchise
    0.18
     Mattress
    0.18
    Developer
    0.17
     Mujer
    0.17
     Stiffness
    0.17
     Collapse
    0.17
     Pern
    0.17
    Მ
    0.17
    Activations Density 0.728%

    No Known Activations