© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15488
    Prev
    Next
    INDEX
    Explanations

    CSS code, specifically related to sizing (height, width, etc.) and layout (position, margin, etc.)

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PerformLayout
    -0.89
    tvguidetime
    -0.75
     initComponents
    -0.75
    makeText
    -0.74
    ]))
    -0.74
    ).]
    -0.73
    GOTREF
    -0.71
    省市镇
    -0.70
    ArgsConstructor
    -0.69
    "]]
    -0.68
    POSITIVE LOGITS
    em
    0.56
    set
    0.49
    rem
    0.49
    str
    0.44
    ns
    0.43
    Em
    0.41
     em
    0.41
    dash
    0.41
    dev
    0.40
    formed
    0.40
    Activations Density 0.874%

    No Known Activations