© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11651
    Prev
    Next
    INDEX
    Explanations

    mentions of someone getting their education

    oai_token-act-pair · gemini-2.0-flash

    words related to practice or training

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

    matching/fields

    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
    principalColumn
    -1.00
    EDEFAULT
    -0.98
     HasFactory
    -0.94
     Италијани
    -0.84
    GraphicsUnit
    -0.81
    withIdentifier
    -0.80
    complexContent
    -0.80
    :+:
    -0.79
    AutoScale
    -0.77
    PropertyChanging
    -0.76
    POSITIVE LOGITS
     rotation
    0.54
     rotations
    0.50
     match
    0.49
     Men
    0.47
    うちに
    0.47
    Match
    0.46
    Matching
    0.45
     men
    0.44
     min
    0.43
     field
    0.42
    Activations Density 1.910%

    No Known Activations