© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10140
    Prev
    Next
    INDEX
    Explanations

    code and punctuation, possibly inside a markup tag, in a non-English language (likely Russian or another Slavic language)

    oai_token-act-pair · gemini-2.0-flash

    code and special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vechi
    -0.56
     eletrônico
    -0.52
     asupra
    -0.50
     Nacionales
    -0.50
     marinho
    -0.49
     Altura
    -0.47
     nici
    -0.47
     nicio
    -0.46
    venidos
    -0.46
     frumos
    -0.46
    POSITIVE LOGITS
     Am
    0.72
     Do
    0.71
     No
    0.67
     Pro
    0.66
     Did
    0.65
     Mo
    0.65
     So
    0.65
     De
    0.64
     To
    0.63
     Are
    0.63
    Activations Density 1.183%

    No Known Activations