© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3373
    Prev
    Next
    INDEX
    Explanations

    text relating to costs and efficiency

    oai_token-act-pair · gemini-2.0-flash

    words related to interpersonal relationships and attitudes

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

    friendly, unfriendly

    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
    abestanden
    -0.60
    Obrázky
    -0.57
     RouterModule
    -0.54
     ExecuteAsync
    -0.52
     ro
    -0.50
    帖最后由
    -0.49
    crollView
    -0.49
    ScopeManager
    -0.49
    selaer
    -0.48
     Waray
    -0.47
    POSITIVE LOGITS
     friendly
    0.77
     Friendly
    0.67
    friendly
    0.66
     unfriendly
    0.66
     neutral
    0.65
     comfortable
    0.65
     amicable
    0.64
     prosperous
    0.62
     agnostic
    0.61
     insensitive
    0.60
    Activations Density 2.521%

    No Known Activations