© 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-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8665
    Prev
    Next
    INDEX
    Explanations

    sentences with the word "I", especially when used with helper verbs like "have" or "'ve"

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    .")
    
    -0.85
     Италијани
    -0.85
     /\.(
    -0.84
    }$​
    -0.82
    .)}
    -0.81
    ."</
    -0.81
    PyExc
    -0.79
     itſelf
    -0.78
    ,:);
    -0.78
    .":
    -0.77
    POSITIVE LOGITS
    ’
    0.88
     have
    0.66
    ”
    0.62
    '
    0.57
    ?
    0.57
     as
    0.47
     get
    0.47
    ís
    0.46
     and
    0.46
     may
    0.46
    Activations Density 1.767%

    No Known Activations