Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9521
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially question marks and exclamation points

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     <=",
    -0.86
     يتيمه
    -0.85
     betweenstory
    -0.83
    fromnode
    -0.76
    protoimpl
    -0.75
     lenker
    -0.71
    Jeografia
    -0.71
    RenderAtEndOf
    -0.68
    出版年
    -0.66
    脚注の使い方
    -0.64
    POSITIVE LOGITS
    •
    0.69
    −
    0.68
     but
    0.64
    ​
    0.63
    //
    0.62
    –
    0.57
    ...
    0.57
    ,
    0.56
    、
    0.56
    [...]
    0.56
    Activations Density 4.381%

    No Known Activations