© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8659
    Prev
    Next
    INDEX
    Explanations

    mentions of phase difference's effect on heat and current in superconducting materials

    oai_token-act-pair · gemini-2.0-flash

    technical terms and syntax

    np_token-act-pair-logits · gpt-4o-mini

    phase

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ^(@)
    -0.85
     Efq
    -0.77
    Personensuche
    -0.74
     leaſt
    -0.72
     myſelf
    -0.70
     nonatomic
    -0.65
     виправивши
    -0.61
     tartalomajánló
    -0.61
    پیوند
    -0.60
    SharedDtor
    -0.60
    POSITIVE LOGITS
     CHtml
    0.56
    currentColor
    0.52
    ()(
    0.49
     الحره
    0.48
    AnchorStyles
    0.46
    AddAttribute
    0.45
    du
    0.45
    TemporalType
    0.45
     depend
    0.44
     ra
    0.44
    Activations Density 4.201%

    No Known Activations