© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6467
    Prev
    Next
    INDEX
    Explanations

    text that describes items arranged in a particular sequence

    oai_token-act-pair · gemini-2.0-flash

    ordering items

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    XmlAccessorType
    -0.82
    sidemargin
    -0.76
    TintMode
    -0.73
     "..\..\..\
    -0.68
     fubject
    -0.64
     snippetHide
    -0.63
    ListItemIcon
    -0.62
    NUMX
    -0.62
    IndentedString
    -0.62
    IVersion
    -0.61
    POSITIVE LOGITS
     متعلقه
    0.52
    Personendaten
    0.47
     lenker
    0.47
    ag
    0.45
    же
    0.45
    part
    0.45
    割
    0.44
    hy
    0.43
    تين
    0.42
    pril
    0.41
    Activations Density 7.036%

    No Known Activations