© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7354
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "i.e." and nearby words, usually in academic papers

    oai_token-act-pair · gemini-2.0-flash

    i.e

    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
     blessés
    -0.59
     mères
    -0.56
     ennemis
    -0.56
    tencent
    -0.52
     donnés
    -0.51
     faibles
    -0.51
     rentrer
    -0.51
     sfera
    -0.51
     fermés
    -0.50
     milliers
    -0.50
    POSITIVE LOGITS
     ModelExpression
    0.96
    IntoConstraints
    0.91
     ſind
    0.77
     doubtnut
    0.72
     Jefus
    0.71
     Majefty
    0.69
     itſelf
    0.69
    ImageContext
    0.68
    . 
    0.68
     ་་
    0.68
    Activations Density 12.767%

    No Known Activations