© 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. 4251
    Prev
    Next
    INDEX
    Explanations

    phrases that include the words "is", "are", and "a/an" which indicate classifying something

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

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

    good, excellent

    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
    createCanvas
    -0.71
    reactstrap
    -0.67
    writeFieldEnd
    -0.63
    <bos>
    -0.61
    PhysRevD
    -0.59
    expandindo
    -0.58
     EconPapers
    -0.58
     TextInputType
    -0.57
    getMenuInflater
    -0.56
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
     good
    2.28
    good
    1.97
     excellent
    1.89
    Good
    1.75
    excellent
    1.67
     Good
    1.60
     GOOD
    1.60
     goede
    1.56
    GOOD
    1.54
    Excellent
    1.52
    Activations Density 1.545%

    No Known Activations