© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1227
    Prev
    Next
    INDEX
    Explanations

    hyphenated words

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    omitempty
    -0.61
     nahilalakip
    -0.52
     >=",
    -0.51
     sumpay
    -0.50
    hoes
    -0.49
    Rè
    -0.47
    acherous
    -0.47
    частли
    -0.47
    encils
    -0.46
    buya
    -0.46
    POSITIVE LOGITS
    IsContent
    0.61
     getItemId
    0.58
    WriteTagHelper
    0.57
     RSSSF
    0.55
     utafitiHapana
    0.54
    abestanden
    0.54
    enderror
    0.53
    "}>
    0.52
    harusnya
    0.52
     hueco
    0.51
    Activations Density 8.245%

    No Known Activations