© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12997
    Prev
    Next
    INDEX
    Explanations

    code relating to reading, writing, and transforming XML and JSON documents

    oai_token-act-pair · gemini-2.0-flash

    X

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ⓧ
    -0.76
     Diſ
    -0.74
     ſtate
    -0.70
     ftate
    -0.67
    клопе
    -0.66
    LookAnd
    -0.66
     octaves
    -0.66
     Anſ
    -0.65
     Eſ
    -0.64
     fevere
    -0.62
    POSITIVE LOGITS
    참고
    0.53
    ie
    0.43
     par
    0.43
    kover
    0.41
    a
    0.39
    zelf
    0.38
     tanto
    0.35
    par
    0.35
     …
    0.35
    ByteArray
    0.35
    Activations Density 3.694%

    No Known Activations