© 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. 9028
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by verbs like said, agreed, or names ending in 'a'.

    oai_token-act-pair · 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
    ourge
    -0.50
    SPD
    -0.49
    MMV
    -0.48
    avits
    -0.47
    Forked
    -0.47
    wendung
    -0.47
    ocarditis
    -0.47
    ulario
    -0.47
    ")));
    -0.46
     const
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.76
    spesies
    0.60
    awtextra
    0.60
    ConstraintMaker
    0.59
    fortawesome
    0.57
     Superhost
    0.55
    DispatchToProps
    0.55
     FetchType
    0.54
    ExtendWith
    0.53
    webElement
    0.53
    Activations Density 0.180%

    No Known Activations