© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5255
    Prev
    Next
    INDEX
    Explanations

    template code using angle brackets

    oai_token-act-pair · gemini-2.0-flash

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    TagHelper
    -3.05
    AndEndTag
    -0.77
    WriteBarrier
    -0.72
    UnknownFieldSet
    -0.71
    IntoConstraints
    -0.68
    cshtml
    -0.67
    ScopeManager
    -0.64
    LayoutStyle
    -0.63
    MethodManager
    -0.63
    StoryboardSegue
    -0.63
    POSITIVE LOGITS
    <bos>
    0.68
     noDo
    0.57
    Editor
    0.54
     Editor
    0.53
    Editors
    0.52
     editor
    0.51
    ')):
    0.51
    TEMPO
    0.51
    kháu
    0.51
    HttpFoundation
    0.50
    Activations Density 0.107%

    No Known Activations