© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13462
    Prev
    Next
    INDEX
    Explanations

    random alphanumeric strings that are likely part of URLs

    oai_token-act-pair · gemini-2.0-flash

    LF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    __':
    -0.57
    DataAnnotations
    -0.56
    token
    -0.55
    reportWebVitals
    -0.54
     TOKEN
    -0.53
    twimg
    -0.52
    TOKEN
    -0.52
     token
    -0.51
    windowFixed
    -0.49
    QByteArray
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.80
     calendriers
    0.74
    PerformLayout
    0.69
    Skocz
    0.65
    abestanden
    0.63
     verona
    0.58
    IndentedString
    0.57
    SharedDtor
    0.57
     tartalomajánló
    0.56
    ารถ
    0.56
    Activations Density 0.145%

    No Known Activations