© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8052
    Prev
    Next
    INDEX
    Explanations

    currency amounts

    oai_token-act-pair · gemini-2.0-flash

    worth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    GEBURTSDATUM
    -0.56
     كورة
    -0.52
     indisponible
    -0.50
    hists
    -0.47
    trise
    -0.47
    yendo
    -0.46
    CastException
    -0.46
     داری
    -0.46
     univerz
    -0.46
    journ
    -0.45
    POSITIVE LOGITS
     worth
    2.66
     Worth
    2.06
     WORTH
    2.00
    Worth
    1.94
    worth
    1.92
    WORTH
    1.63
     worthwhile
    1.15
     worthy
    1.10
    worths
    1.01
    值得
    0.98
    Activations Density 0.788%

    No Known Activations