© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11599
    Prev
    Next
    INDEX
    Explanations

    adverbs such as "thus", and the phrase "so far" or "this far"

    oai_token-act-pair · gemini-2.0-flash

    Random text fragments

    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
     far
    -2.48
    far
    -2.39
    Far
    -2.31
     Far
    -2.25
     FAR
    -1.93
    FAR
    -1.86
    远
    -1.61
     farthest
    -1.59
     jauh
    -1.51
     furthest
    -1.48
    POSITIVE LOGITS
    olism
    0.69
    UAWEI
    0.54
    省市镇
    0.51
    documentElement
    0.50
    getJSONArray
    0.47
     StringTokenizer
    0.45
    kuuta
    0.43
    ptons
    0.43
     htons
    0.43
     Layton
    0.43
    Activations Density 1.161%

    No Known Activations