© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3184
    Prev
    Next
    INDEX
    Explanations

    words related to analysis and code, especially when discussing how and when something is used

    oai_token-act-pair · gemini-2.0-flash

    some

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    archiviato
    -0.64
     itſelf
    -0.56
     viewDidLoad
    -0.56
    atilde
    -0.55
     Majefty
    -0.54
     gloire
    -0.53
    ніципалі
    -0.52
     ditto
    -0.51
     незавершена
    -0.51
     acuerdo
    -0.50
    POSITIVE LOGITS
     some
    2.69
    some
    2.23
     Some
    2.09
    Some
    2.02
     SOME
    1.77
    SOME
    1.66
     algunos
    1.56
     algunas
    1.53
     alguns
    1.47
     algumas
    1.40
    Activations Density 3.290%

    No Known Activations