© 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. 14618
    Prev
    Next
    INDEX
    Explanations

    a wide variety of common verbs and contractions.

    oai_token-act-pair · gemini-2.0-flash

    "s"

    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
     adultery
    -0.57
     вікі
    -0.55
     captivity
    -0.54
     zelve
    -0.54
     trident
    -0.52
    EDEFAULT
    -0.52
    ThroughAttribute
    -0.52
    EndProject
    -0.50
     esternos
    -0.50
     "..\..\
    -0.50
    POSITIVE LOGITS
    <bos>
    0.87
    SBATCH
    0.56
     voilà
    0.52
     الحره
    0.49
    τούν
    0.47
    ("]");
    0.44
    The
    0.44
    smithy
    0.43
     positioned
    0.43
     The
    0.43
    Activations Density 3.080%

    No Known Activations