© 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. 13555
    Prev
    Next
    INDEX
    Explanations

    a mixture of numeric values, words associated with measurement, and present tense verbs

    oai_token-act-pair · 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
    EndInit
    -0.91
    StructEnd
    -0.88
    PreferredItem
    -0.85
    mybatisplus
    -0.81
    raszam
    -0.75
    StoryboardSegue
    -0.75
    RunAsync
    -0.73
    wpi
    -0.73
    horabuena
    -0.73
    Rohy
    -0.72
    POSITIVE LOGITS
    \{\\
    0.58
    TreeNode
    0.49
    <eos>
    0.43
    держка
    0.43
    чу
    0.42
    Node
    0.42
    aver
    0.41
     
    0.39
    cdnjs
    0.39
     reda
    0.38
    Activations Density 4.443%

    No Known Activations