© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14630
    Prev
    Next
    INDEX
    Explanations

    image formatting tags

    oai_token-act-pair · gemini-2.0-flash

    textwidth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    setVerticalGroup
    -0.93
    出版年
    -0.92
    :✨
    -0.90
    bootstrapcdn
    -0.90
     Houſe
    -0.87
    apatalk
    -0.84
    +:+
    -0.83
     Reſ
    -0.81
    twimg
    -0.81
    SourceChecksum
    -0.80
    POSITIVE LOGITS
    <em>
    0.40
    re
    0.38
    曖昧さ回避
    0.37
    A
    0.37
     baru
    0.36
    <bos>
    0.35
    1
    0.35
    2
    0.35
     aged
    0.34
    /
    0.34
    Activations Density 0.294%

    No Known Activations