© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2292
    Prev
    Next
    INDEX
    Explanations

    C language code with networking and UI elements

    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_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    InstanceState
    -0.48
     alike
    -0.47
     snippetHide
    -0.44
    alog
    -0.44
    מון
    -0.43
     Etter
    -0.43
     ISNI
    -0.42
    tover
    -0.41
    ้าย
    -0.41
     opposite
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.77
     disambiguazione
    0.74
    writeField
    0.74
    providedIn
    0.71
     kasarigan
    0.70
    UnsafeEnabled
    0.68
    GEBURTS
    0.64
    +#+#
    0.64
     autorytatywna
    0.63
    IVEREF
    0.63
    Activations Density 5.277%

    No Known Activations