© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8705
    Prev
    Next
    INDEX
    Explanations

    the digit "2" followed by several digits, especially "2119" and "211932"

    oai_token-act-pair · gemini-2.0-flash

    one

    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
     defaultstate
    -0.57
     mourut
    -0.56
    XmlAccessType
    -0.55
    /***/
    -0.54
    ILLS
    -0.54
    dafx
    -0.54
    QMetaType
    -0.52
    انيف
    -0.50
     admit
    -0.49
    誼
    -0.48
    POSITIVE LOGITS
    LEncoder
    0.60
    tvguidetime
    0.54
    Personendaten
    0.53
    lao
    0.52
     impossibile
    0.50
    Begriffsklä
    0.48
    GeneratedCode
    0.48
    ValueStyle
    0.48
    mena
    0.45
    mok
    0.45
    Activations Density 1.956%

    No Known Activations