© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12914
    Prev
    Next
    INDEX
    Explanations

    the french character 'Ã'

    oai_token-act-pair · gemini-2.0-flash

    Ã

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    XmlRootElement
    -0.62
    Predecesor
    -0.55
     Jezus
    -0.55
    XmlAccessorType
    -0.54
    ContextHolder
    -0.54
     createContext
    -0.51
    AutoScaleMode
    -0.51
    ,:)
    -0.49
    TacToe
    -0.49
     vuitton
    -0.49
    POSITIVE LOGITS
    éry
    0.52
    principalColumn
    0.52
    xam
    0.46
     Мексичка
    0.45
    قایناقلار
    0.45
     regen
    0.45
     Horn
    0.44
     Chwiliwch
    0.43
     CURLOPT
    0.43
    messageInfo
    0.43
    Activations Density 0.383%

    No Known Activations