© 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. 3271
    Prev
    Next
    INDEX
    Explanations

    references to licenses and files

    oai_token-act-pair · gemini-2.0-flash

    Code and licensing

    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
    AndEndTag
    -0.64
    новниш
    -0.56
    mybatisplus
    -0.54
    !("{}",
    -0.50
    databind
    -0.49
    !("{
    -0.48
    ystema
    -0.47
     Klagen
    -0.47
     Italijani
    -0.47
    gså
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.70
    PYX
    0.64
    IVEREF
    0.63
     BoxFit
    0.61
     harian
    0.55
     autorytatywna
    0.54
    XmlAccessType
    0.52
     useCallback
    0.51
    pecha
    0.49
     typelib
    0.48
    Activations Density 0.596%

    No Known Activations