© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9995
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    specific scientific notation or formal expressions

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

    physics

    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
    EndInit
    -0.72
     newOwner
    -0.64
     bezeichneter
    -0.59
     урна
    -0.55
     isComment
    -0.54
    ModelSerializer
    -0.53
    principalColumn
    -0.53
    moreland
    -0.53
    complexType
    -0.52
     Poles
    -0.52
    POSITIVE LOGITS
    AppMethodBeat
    0.53
    原始内容存档于
    0.49
     call
    0.46
    袤
    0.45
     object
    0.45
     All
    0.44
    nyv
    0.44
     годов
    0.43
    Viited
    0.42
    ază
    0.42
    Activations Density 2.603%

    No Known Activations