© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4354
    Prev
    Next
    INDEX
    Explanations

    the letters "tf" and mathematical terms in equations, particularly in code and scientific texts

    oai_token-act-pair · gemini-2.0-flash

    tf, term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     tf
    -1.15
    tf
    -1.14
    TF
    -0.75
     TF
    -0.73
     torch
    -0.56
    tb
    -0.55
    Tf
    -0.54
    RenderAtEndOf
    -0.50
    torch
    -0.50
    PerformLayout
    -0.47
    POSITIVE LOGITS
    sidemargin
    0.88
    Sucesor
    0.79
     AttributeSet
    0.76
    NameInMap
    0.75
     للاسماء
    0.72
    subpackage
    0.68
    ✨:
    0.66
     Савезне
    0.66
    rawDesc
    0.62
     ModelExpression
    0.62
    Activations Density 0.599%

    No Known Activations