© 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. 4634
    Prev
    Next
    INDEX
    Explanations

    contexts where something is done to prevent loss or damage

    oai_token-act-pair · gemini-2.0-flash

    product descriptions/instructions

    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
    Portale
    -0.77
    tagHelperRunner
    -0.75
     kasarigan
    -0.71
    VersionUID
    -0.69
     useDispatch
    -0.69
     חיצוניים
    -0.66
    __':
    -0.64
    HasAnnotation
    -0.63
    __":
    -0.63
    UnusedPrivate
    -0.60
    POSITIVE LOGITS
     multi
    0.47
    astéroïdes
    0.46
    lanmış
    0.45
     zom
    0.45
     d
    0.44
    kinen
    0.43
    ribune
    0.43
    isfile
    0.43
    ashqai
    0.43
    angue
    0.42
    Activations Density 1.209%

    No Known Activations