© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4235
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related keywords

    oai_token-act-pair · gemini-2.0-flash

    body

    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
    esez
    -0.51
     AppComponent
    -0.49
    ดง
    -0.49
    rrggbb
    -0.49
    TagMode
    -0.48
    toFloat
    -0.48
    WebVitals
    -0.46
    HomeAsUpEnabled
    -0.45
     متعلقه
    -0.45
     ExecuteAsync
    -0.44
    POSITIVE LOGITS
    IntoConstraints
    0.61
    orianCalendar
    0.60
    SizeF
    0.60
     صوتيه
    0.58
     Enix
    0.56
    <bos>
    0.56
    AnchorTagHelper
    0.54
    acm
    0.52
     AllMovie
    0.50
    śmy
    0.47
    Activations Density 2.220%

    No Known Activations