© 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. 13601
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a request for help or gratitude, often related to technical issues

    oai_token-act-pair · gemini-2.0-flash

    numerical values in a sequence

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

    programming help requests

    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
     '\\;'
    -0.75
    הערות
    -0.71
    Билгалдахарш
    -0.68
    
    -0.59
     ogóle
    -0.58
    abestanden
    -0.56
     TPE
    -0.53
    avance
    -0.52
     kasarigan
    -0.52
    IContainer
    -0.52
    POSITIVE LOGITS
    TargetException
    0.64
     three
    0.63
    mockito
    0.61
     five
    0.59
     in
    0.59
     six
    0.59
     nine
    0.58
     ten
    0.56
     eight
    0.54
     seven
    0.54
    Activations Density 7.567%

    No Known Activations