© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5080
    Prev
    Next
    INDEX
    Explanations

    movie and book review snippets, and place and family member names

    oai_token-act-pair · gemini-2.0-flash

    Code identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    CurrentPage
    -0.59
     CURIAM
    -0.56
    OMON
    -0.55
     erat
    -0.54
    ransition
    -0.54
    новништво
    -0.53
    脚注の使い方
    -0.52
    cfm
    -0.52
    aronder
    -0.52
    edia
    -0.52
    POSITIVE LOGITS
    LoadScene
    0.52
    //});
    0.51
    uminense
    0.49
     makeStyles
    0.48
     című
    0.47
    parsedMessage
    0.47
    TypedDataSet
    0.47
    featureID
    0.46
     Drapeau
    0.46
    Espèce
    0.45
    Activations Density 3.305%

    No Known Activations