© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5895
    Prev
    Next
    INDEX
    Explanations

    honorifics like Mr. and Dr., often followed by periods, and words associated with official titles, locations, institutions, and formal procedures.

    oai_token-act-pair · gemini-2.0-flash

    Titles and names

    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
    ](#
    -0.36
     (§
    -0.34
     if
    -0.32
     IBOutlet
    -0.31
     If
    -0.30
    로그인
    -0.30
     ☐
    -0.30
     ReactDOM
    -0.30
     elif
    -0.30
     iff
    -0.29
    POSITIVE LOGITS
     religieuses
    0.60
     kasarigan
    0.59
     démocr
    0.58
     églises
    0.58
     traités
    0.58
     financières
    0.57
    føre
    0.56
     découver
    0.55
     européennes
    0.55
    fører
    0.55
    Activations Density 16.744%

    No Known Activations