© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10497
    Prev
    Next
    INDEX
    Explanations

    strings of digits, often within larger ID strings

    oai_token-act-pair · gemini-2.0-flash

    code/data strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Portale
    -0.58
     ويكيميديا
    -0.48
    lehrer
    -0.48
    aneta
    -0.47
     PARSER
    -0.47
    انيف
    -0.45
     Avis
    -0.45
     noqa
    -0.44
    áo
    -0.44
     вра
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.73
     monasterio
    0.62
     noft
    0.62
     habet
    0.61
    guisement
    0.59
    alnız
    0.57
     quæ
    0.57
     antidepress
    0.56
     JpaRepository
    0.56
     @"/
    0.56
    Activations Density 2.884%

    No Known Activations