© 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. 10469
    Prev
    Next
    INDEX
    Explanations

    hyphens surrounded by numbers or whitespace.

    oai_token-act-pair · gemini-2.0-flash

    -

    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
    -
    -0.55
     paci
    -0.43
    (
    -0.42
    expandindo
    -0.42
    "
    -0.39
     Voit
    -0.39
    Przypisy
    -0.35
     domesti
    -0.33
     erit
    -0.33
     obiec
    -0.32
    POSITIVE LOGITS
    AddTagHelper
    0.69
    khó
    0.60
    Diámetro
    0.59
    PLATE
    0.58
    sticks
    0.57
    nett
    0.57
    loem
    0.57
    yto
    0.57
     viewDid
    0.56
     Meksiku
    0.55
    Activations Density 6.982%

    No Known Activations