© 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. 4267
    Prev
    Next
    INDEX
    Explanations

    React code which includes "console.log", "this.setState", "return", and "<View"

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    Sucesor
    -0.88
    ArgsConstructor
    -0.85
    NUMX
    -0.84
    principalColumn
    -0.83
    extAlignment
    -0.79
    StructEnd
    -0.78
     Majefty
    -0.78
    MemoryWarning
    -0.76
     betweenstory
    -0.76
    expandindo
    -0.75
    POSITIVE LOGITS
    所で
    0.41
     ayude
    0.41
     khu
    0.40
    ↵↵
    0.39
     perdeu
    0.39
    felde
    0.38
    auth
    0.38
    akuza
    0.37
    sort
    0.37
    shout
    0.35
    Activations Density 1.718%

    No Known Activations