Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10413
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to bartering or misidentification of one thing for another.

    oai_token-act-pair · gemini-2.0-flash

    "for"

    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
    gonic
    -0.82
    \{\\
    -0.76
    WithIOException
    -0.75
    GEBURTSDATUM
    -0.70
    MemoryWarning
    -0.66
     eventdata
    -0.65
    UpInside
    -0.65
    DockStyle
    -0.65
    >{@
    -0.64
    istoitu
    -0.63
    POSITIVE LOGITS
     for
    1.40
    for
    1.12
     FOR
    0.81
    For
    0.79
     For
    0.75
     för
    0.73
     voor
    0.72
     für
    0.70
     за
    0.68
     pentru
    0.68
    Activations Density 1.167%

    No Known Activations