© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    4. 91
    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_2_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
    :\
    0.15
    ن
    0.14
     ERK
    0.13
     इसे
    0.13
     растение
    0.13
    fontsize
    0.13
     число
    0.13
    CIA
    0.13
     ef
    0.13
    न
    0.13
    POSITIVE LOGITS
    at
    0.18
    ം
    0.16
    ה
    0.15
    ค์
    0.15
    ición
    0.15
    Ź
    0.14
    लिये
    0.14
    ות
    0.13
    aringan
    0.13
     nonché
    0.13
    Activations Density 0.553%

    No Known Activations