© 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. 4006
    Prev
    Next
    INDEX
    Explanations

    code snippets with symbols such as :, [], and ;

    oai_token-act-pair · gemini-2.0-flash

    code syntax

    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
     صوتيه
    -0.63
     فريبيس
    -0.63
    <bos>
    -0.60
    IContainer
    -0.60
     disponibilités
    -0.57
     saites
    -0.56
     utafitiHapana
    -0.55
    ⎩
    -0.55
    \{\\
    -0.54
    ModelBuilder
    -0.54
    POSITIVE LOGITS
     harde
    0.52
    一種
    0.52
    thur
    0.47
    这样
    0.46
     ordinary
    0.46
    ợt
    0.46
     ([]
    0.45
    わずか
    0.44
    וויק
    0.44
     consultato
    0.44
    Activations Density 15.106%

    No Known Activations