© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11075
    Prev
    Next
    INDEX
    Explanations

    words often found in conversational english and dialog, and words associated with competitions.

    oai_token-act-pair · gemini-2.0-flash

    Employment and job search

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     chère
    -0.49
    WithIOException
    -0.46
     favoritos
    -0.45
     próprios
    -0.45
     AssemblyProduct
    -0.42
     ^(
    -0.42
     كومونز
    -0.41
    titure
    -0.40
     prefi
    -0.39
    chap
    -0.38
    POSITIVE LOGITS
    exitRule
    0.65
    DockStyle
    0.63
    pya
    0.60
    __*/
    0.59
     >=",
    0.58
    fetchone
    0.57
     VIDEOTAPE
    0.57
    parsedMessage
    0.56
    tagHelperRunner
    0.56
     resourceCulture
    0.55
    Activations Density 2.167%

    No Known Activations