© 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. 13533
    Prev
    Next
    INDEX
    Explanations

    web development resources like file paths and javascript libraries

    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_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
    <bos>
    -0.62
    toBeTruthy
    -0.50
     key
    -0.43
    .
    -0.41
    (
    -0.40
     клю
    -0.40
     commonly
    -0.39
    !
    -0.38
     keys
    -0.38
    彼が
    -0.38
    POSITIVE LOGITS
    AndEndTag
    0.84
    tagHelperRunner
    0.79
    UIControlState
    0.77
    TypedDataSet
    0.75
     calendriers
    0.70
     GoogleFonts
    0.69
    featureID
    0.69
    ContentAsync
    0.67
     مشين
    0.67
    IVEREF
    0.62
    Activations Density 3.319%

    No Known Activations