© 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. 12765
    Prev
    Next
    INDEX
    Explanations

    words, affixes, and phrases used to relate one research finding to another

    oai_token-act-pair · gemini-2.0-flash

    academic/legal writing

    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
    WebVitals
    -0.63
    UIControlState
    -0.57
    UrlResolution
    -0.56
    igshid
    -0.54
    ế
    -0.51
    principalTable
    -0.50
    "]
    -0.50
    letal
    -0.50
    exion
    -0.49
    CompleteListener
    -0.49
    POSITIVE LOGITS
    ografija
    0.64
    <bos>
    0.63
    NameInMap
    0.61
    Viitteet
    0.59
     الحره
    0.59
     onCreateView
    0.54
    fitriones
    0.50
     hindurch
    0.49
     prieten
    0.48
    MockBean
    0.47
    Activations Density 10.363%

    No Known Activations