© 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. 159
    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
    Observable
    0.17
    ことは
    0.16
    irsty
    0.15
    このような
    0.15
    その後
    0.15
    டிப்ப
    0.15
    딪
    0.15
     छत्तीस
    0.15
    फ्ते
    0.15
     subsequent
    0.15
    POSITIVE LOGITS
     Для
    0.22
     retomar
    0.21
    ಿಸಲು
    0.21
     ច
    0.20
    䚰
    0.20
     Pentru
    0.20
     novamente
    0.20
     especiais
    0.20
     conhecido
    0.20
    ocultural
    0.20
    Activations Density 0.637%

    No Known Activations