© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16112
    Prev
    Next
    INDEX
    Explanations

    code, numbers, and technical writing

    oai_token-act-pair · gemini-2.0-flash

    numerical data/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    OrNil
    -0.52
     AdapterView
    -0.48
    addPreferredGap
    -0.47
    bledon
    -0.46
     دیکھیے
    -0.46
     actual
    -0.45
    webElementGuid
    -0.45
     supersede
    -0.45
     utilisation
    -0.45
    ukunft
    -0.44
    POSITIVE LOGITS
    ########.
    0.73
     propOrder
    0.66
    SharedDtor
    0.63
    DataAnnotations
    0.63
    WireFormatLite
    0.61
    IVEREF
    0.60
    دانشنامهٔ
    0.57
    ówczas
    0.55
    Ծանոթ
    0.53
    ❋
    0.52
    Activations Density 13.240%

    No Known Activations