© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10125
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns followed by verbs expressing knowledge, emotions and intent

    oai_token-act-pair · gemini-2.0-flash

    I am, I know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ">//
    -0.78
    esez
    -0.75
    intenant
    -0.74
     Paglinawan
    -0.73
     []:
    -0.73
     nahilalakip
    -0.72
    glUniform
    -0.70
    !*\
    -0.66
    ///</
    -0.66
     nakalista
    -0.66
    POSITIVE LOGITS
     MHD
    0.52
    వు
    0.50
     esistono
    0.49
    vő
    0.48
     willows
    0.47
     esiste
    0.47
     transposition
    0.47
     plagio
    0.46
     yako
    0.46
     initComponents
    0.45
    Activations Density 0.619%

    No Known Activations