© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11252
    Prev
    Next
    INDEX
    Explanations

    technical descriptions in the realm of physics and electrical engineering.

    oai_token-act-pair · gemini-2.0-flash

    charge carriers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    enumii
    -0.51
    Зву
    -0.47
     enquiry
    -0.44
     joke
    -0.43
    읽
    -0.42
    bestos
    -0.42
    standig
    -0.42
    󠁢
    -0.41
    niosek
    -0.39
     bullet
    -0.39
    POSITIVE LOGITS
    IsMutable
    0.82
    ValueStyle
    0.77
    AccessorTable
    0.76
    TypedDataSet
    0.73
     كومونز
    0.72
    tagHelperRunner
    0.69
    ThroughAttribute
    0.69
    basicConfig
    0.68
    sizeCache
    0.68
    NameInMap
    0.68
    Activations Density 26.015%

    No Known Activations