© 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. 82
    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_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
     danne
    0.11
     oors
    0.11
     Zamb
    0.10
    രെ
    0.10
    ㎿
    0.10
     Caribe
    0.10
    czny
    0.10
    ？！
    0.10
    历史上
    0.10
    വാസ
    0.10
    POSITIVE LOGITS
    Ло
    0.13
    Optical
    0.12
    к
    0.12
    और
    0.11
    Ook
    0.11
     மட்டும்
    0.11
    酮
    0.11
    eliminate
    0.11
    Бо
    0.11
    EXTRA
    0.11
    Activations Density 4.318%

    No Known Activations