© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5419
    Prev
    Next
    INDEX
    Explanations

    a jumble of seemingly unrelated concepts including code snippets, math symbols, legal terminology, and references to disorders

    oai_token-act-pair · gemini-2.0-flash

    parenthesis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     (
    -0.76
     }}(
    -0.69
    "](
    -0.59
    ')(
    -0.56
    ")(
    -0.55
    /#{
    -0.55
    '][
    -0.54
     '
    -0.54
    ))(
    -0.54
     ‘
    -0.54
    POSITIVE LOGITS
     ("
    1.10
     (“
    1.06
     („
    1.01
     («
    1.00
     ('
    0.88
     ($\
    0.85
     (‘
    0.81
    ("
    0.80
    (“
    0.79
    ('
    0.73
    Activations Density 5.416%

    No Known Activations