© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14486
    Prev
    Next
    INDEX
    Explanations

    the number six, particularly numerical quantities and references to chemical or biological compounds

    oai_token-act-pair · gemini-2.0-flash

    six

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    6
    -1.14
     six
    -1.05
    Personendaten
    -0.97
    Portail
    -0.96
     Six
    -0.95
     Sixty
    -0.94
    Sixty
    -0.90
    Six
    -0.88
    六
    -0.85
    six
    -0.84
    POSITIVE LOGITS
    ajur
    0.48
    enius
    0.47
    madan
    0.47
    漏れ
    0.47
     ».
    0.47
    "…
    0.45
     dừa
    0.43
    leuchte
    0.43
    XmlIgnore
    0.43
     (!(
    0.43
    Activations Density 1.756%

    No Known Activations