© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8053
    Prev
    Next
    INDEX
    Explanations

    instances of the first-person pronoun "I"

    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_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
    hols
    -0.63
    
    -0.54
    heds
    -0.51
     primas
    -0.51
     sol
    -0.50
    chek
    -0.49
    pecto
    -0.49
    údo
    -0.47
     SOL
    -0.47
     Capo
    -0.47
    POSITIVE LOGITS
     unknownFields
    0.65
    aarrggbb
    0.64
     виправивши
    0.60
    Bioaccumulative
    0.57
     estekak
    0.56
    protoimpl
    0.54
    rrggbb
    0.54
    nteral
    0.52
     typelib
    0.52
     setempat
    0.49
    Activations Density 3.935%

    No Known Activations