© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11256
    Prev
    Next
    INDEX
    Explanations

    articles "the", "a", "an", "her", "their" and pronouns "it", "was" and "is" that connect concepts within narratives or explanations.

    oai_token-act-pair · gemini-2.0-flash

    news stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ########.
    -0.63
     transférez
    -0.60
     giudizio
    -0.58
     vägen
    -0.58
     tramonto
    -0.57
     illustrazione
    -0.56
    ñora
    -0.55
     vocale
    -0.55
     conseguenza
    -0.54
     kvä
    -0.54
    POSITIVE LOGITS
    )];
    0.66
     final
    0.62
    ']").
    0.59
     eventual
    0.56
     Efq
    0.56
     fifties
    0.55
     }}$}
    0.55
    Rüyada
    0.55
     remainder
    0.55
    ']).
    0.55
    Activations Density 6.480%

    No Known Activations