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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14773
    Prev
    Next
    INDEX
    Explanations

    descriptions of the direction of sound and connections in electronics

    oai_token-act-pair · gemini-2.0-flash

    forward direction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    JspWriter
    -0.60
    __);
    -0.59
    ftagPool
    -0.54
     Voi
    -0.47
     externas
    -0.47
     hashlib
    -0.47
    mapStateToProps
    -0.46
    cdnjs
    -0.45
    wide
    -0.45
     malta
    -0.45
    POSITIVE LOGITS
     ahead
    1.24
    ahead
    1.16
     Ahead
    1.09
     AHEAD
    1.07
     front
    1.03
    Ahead
    0.99
     delante
    0.96
    front
    0.92
     forward
    0.91
     hadapan
    0.90
    Activations Density 1.098%

    No Known Activations