© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15276
    Prev
    Next
    INDEX
    Explanations

    sequences of tokens that represent broadcast television stations

    oai_token-act-pair · gemini-2.0-flash

    Dallas sports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tvguidetime
    -0.72
    omeness
    -0.71
    ChildScrollView
    -0.69
     autorytatywna
    -0.68
    ########.
    -0.67
     VizieR
    -0.66
     BorderSide
    -0.66
    المناصب
    -0.66
    RenderAtEndOf
    -0.66
    setupUi
    -0.65
    POSITIVE LOGITS
    alte
    0.52
    rn
    0.47
    ced
    0.47
    pi
    0.46
     tr
    0.45
    acha
    0.44
    sey
    0.44
     ti
    0.43
     digital
    0.43
     di
    0.43
    Activations Density 0.385%

    No Known Activations