© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2267
    Prev
    Next
    INDEX
    Explanations

    words related to legal or scientific research like testimony, detection, interrupt, or publication

    oai_token-act-pair · gemini-2.0-flash

    examinations/experiments

    np_max-act · gemini-2.0-flash

    examination

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     
    -0.85
    ’
    -0.83
    '
    -0.81
    .
    -0.75
    ↵
    -0.69
    ."
    -0.68
    "
    -0.67
    ",
    -0.67
     (
    -0.65
    ,
    -0.65
    POSITIVE LOGITS
    LookAnd
    1.10
     Roskov
    1.06
    oa̍t
    1.04
     myſelf
    1.04
    expandindo
    1.00
    ⓧ
    1.00
     betweenstory
    1.00
    sizeCache
    0.99
    MLLoader
    0.99
     nakalista
    0.98
    Activations Density 84.540%

    No Known Activations