© 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. 10956
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets and related strings (filenames, error messages, etc.) with high confidence

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    featureID
    -0.70
    lateinit
    -0.58
    PreferredItem
    -0.57
    deth
    -0.55
     lateinit
    -0.54
    OPO
    -0.50
     %>%
    -0.50
    Vegeu
    -0.49
    nemonic
    -0.49
    mechanism
    -0.48
    POSITIVE LOGITS
     nakalista
    0.64
     domanda
    0.58
     بيها
    0.57
     kaarangay
    0.56
     вікі
    0.54
    المناصب
    0.54
     démocratie
    0.53
     transferência
    0.53
     digress
    0.52
    schild
    0.52
    Activations Density 10.619%

    No Known Activations