© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14645
    Prev
    Next
    INDEX
    Explanations

    names followed by verbs or words related to actions

    oai_token-act-pair · gemini-2.0-flash

    legal/biographical contexts

    np_max-act · gemini-2.0-flash
    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
    WithMany
    -0.57
    که
    -0.54
    mobileqq
    -0.50
    iligt
    -0.50
     numberOfRows
    -0.49
    titleMargin
    -0.48
    windowFixed
    -0.48
     SEDS
    -0.47
    ÚBL
    -0.47
    SECUR
    -0.47
    POSITIVE LOGITS
    <bos>
    0.92
    __":
    0.71
    verwijspagina
    0.65
    __':
    0.58
     AssemblyCulture
    0.53
    besondere
    0.49
    setError
    0.49
    razine
    0.48
    ysuckle
    0.46
     Garibaldi
    0.46
    Activations Density 2.854%

    No Known Activations