© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14716
    Prev
    Next
    INDEX
    Explanations

    words that express some kind of relationship, whether it be a name, date, or as a descriptor.

    oai_token-act-pair · gemini-2.0-flash

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -0.62
    BASEPATH
    -0.54
    הערות
    -0.50
    cookieParser
    -0.49
    Erstellt
    -0.48
    redientes
    -0.47
    Ә
    -0.45
    VersionUID
    -0.45
    CMake
    -0.44
    槛
    -0.44
    POSITIVE LOGITS
     PyLong
    0.64
     rağmen
    0.56
     vectorielles
    0.56
    riller
    0.54
    ävän
    0.54
     leçons
    0.54
    paksa
    0.54
     fût
    0.53
    mappedBy
    0.53
    glTranslatef
    0.52
    Activations Density 2.047%

    No Known Activations