© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5107
    Prev
    Next
    INDEX
    Explanations

    complex sentences describing historical events and related discussions, often involving dates, treaties, and political figures.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
     bénévoles
    -0.57
     preghi
    -0.56
     réguli
    -0.56
     preghiera
    -0.55
     inalámb
    -0.54
     operazioni
    -0.54
     béné
    -0.54
     käyttö
    -0.53
     mélanger
    -0.53
     trattato
    -0.53
    POSITIVE LOGITS
    __*/
    0.54
    yonel
    0.50
    SourceChecksum
    0.50
     Dernière
    0.48
     []:
    0.48
    PageRoute
    0.48
    ity
    0.47
    /***/
    0.46
    parseFrom
    0.45
     /\.(
    0.45
    Activations Density 1.756%

    No Known Activations