© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11818
    Prev
    Next
    INDEX
    Explanations

    words that indicate position and orientation with an emphasis on "facing down"

    oai_token-act-pair · gemini-2.0-flash

    physical orientation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     esfuer
    -0.58
     nltk
    -0.55
    ModelAttribute
    -0.53
    ManagedBean
    -0.50
     onOptions
    -0.50
    kling
    -0.48
    ModelBuilder
    -0.47
    lodash
    -0.47
    lessly
    -0.46
    getPassword
    -0.46
    POSITIVE LOGITS
    GEBURTSDATUM
    0.77
     NSCoder
    0.70
     facing
    0.67
     beginnetje
    0.65
     Wikimedijinoj
    0.65
     unknownFields
    0.63
    Personendaten
    0.62
    OGND
    0.62
    UrlResolution
    0.62
    RenderAtEndOf
    0.61
    Activations Density 1.076%

    No Known Activations