© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4142
    Prev
    Next
    INDEX
    Explanations

    scientific data, metrics, and notation

    oai_token-act-pair · gemini-2.0-flash

    numeric values and percentages

    np_token-act-pair-logits · gpt-4o-mini

    say "zero related"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    extAlignment
    -0.84
    ſhip
    -0.77
    NUMX
    -0.75
    leſs
    -0.75
    AndEndTag
    -0.75
    IntoConstraints
    -0.75
    GEBURTSDATUM
    -0.75
    LabelTagHelper
    -0.74
    Географи
    -0.74
    HasBeenSet
    -0.74
    POSITIVE LOGITS
    0
    0.66
    5
    0.61
    %
    0.58
    6
    0.58
    w
    0.54
    4
    0.54
    x
    0.53
    7
    0.52
    8
    0.52
    3
    0.52
    Activations Density 13.699%

    No Known Activations