© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2365
    Prev
    Next
    INDEX
    Explanations

    error handling code

    oai_token-act-pair · gemini-2.0-flash

    nil

    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
     nil
    -1.37
    <bos>
    -1.04
    nil
    -1.01
    Nil
    -0.85
     Nil
    -0.70
     NIL
    -0.64
    NIL
    -0.55
    #
    -0.49
    aarrggbb
    -0.48
     autorytatywna
    -0.48
    POSITIVE LOGITS
    Personensuche
    0.59
    hunter
    0.59
    eqn
    0.58
    featureID
    0.58
    SupportActionBar
    0.57
    Sinon
    0.57
    :✨
    0.55
    ichiro
    0.55
     disambiguazione
    0.53
    OnDelete
    0.52
    Activations Density 0.415%

    No Known Activations