© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9087
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms, also with Spanish words mixed in

    oai_token-act-pair · gemini-2.0-flash

    code and non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    shadowOpacity
    -0.59
     (£
    -0.59
    mybatisplus
    -0.58
     coger
    -0.57
     déclaration
    -0.56
     rembour
    -0.56
     AdapterView
    -0.56
     neuter
    -0.56
     timescale
    -0.55
     nigra
    -0.54
    POSITIVE LOGITS
    RTEE
    0.65
    Архівовано
    0.59
    олові
    0.59
    yntaxException
    0.49
     لينك
    0.48
    Portale
    0.47
    ViewFeatures
    0.47
    MigrationBuilder
    0.47
     econô
    0.45
    Abraços
    0.45
    Activations Density 1.884%

    No Known Activations