© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12227
    Prev
    Next
    INDEX
    Explanations

    lines of code, especially those which reference CPU, compilers, or memory

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    "]).
    -1.06
    "),
    -1.03
    ")}
    -0.97
    ")]
    -0.93
     "]
    -0.91
    ")
    -0.91
    ")).
    -0.91
    ")]
    -0.91
    "]
    -0.91
    "]:
    -0.90
    POSITIVE LOGITS
    <bos>
    1.00
     autorytatywna
    0.75
    protoimpl
    0.75
    mybatisplus
    0.68
    zzleHttp
    0.67
     circumcision
    0.65
    StructEnd
    0.64
    ConstraintMaker
    0.62
     '\\;'
    0.62
    InjectAttribute
    0.62
    Activations Density 0.673%

    No Known Activations