© 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. 4454
    Prev
    Next
    INDEX
    Explanations

    words or phrases that describe differences or changes.

    oai_token-act-pair · gemini-2.0-flash

    adverbs indicating degree

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

    High degree

    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
    liggende
    -0.54
    setContentView
    -0.54
    seamnă
    -0.52
     humanas
    -0.48
     nevoie
    -0.46
    urés
    -0.44
     motivadoras
    -0.43
    ariest
    -0.43
    toje
    -0.41
     către
    -0.41
    POSITIVE LOGITS
     significantly
    1.93
     greatly
    1.88
     substantially
    1.80
     drastically
    1.73
     considerably
    1.72
     dramatically
    1.66
     markedly
    1.66
    significantly
    1.60
     heavily
    1.59
     severely
    1.57
    Activations Density 3.718%

    No Known Activations