© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9729
    Prev
    Next
    INDEX
    Explanations

    words that start or end a scientific paragraph, including section headers, experimental setup, and the phrase "to [verb]"

    oai_token-act-pair · gemini-2.0-flash

    To

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    BeginContext
    -0.53
     JADX
    -0.47
    bootstrapcdn
    -0.43
    que
    -0.43
    folgen
    -0.41
    ABUL
    -0.41
     ash
    -0.41
     check
    -0.41
    ту
    -0.41
    aca
    -0.41
    POSITIVE LOGITS
    tableFuture
    0.79
    MLLoader
    0.76
     AssemblyProduct
    0.74
    erdings
    0.74
     كومونز
    0.73
     calendriers
    0.67
     AssemblyTitle
    0.65
     ExecuteAsync
    0.65
    ThroughAttribute
    0.64
    OGND
    0.63
    Activations Density 1.833%

    No Known Activations