© 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. 8977
    Prev
    Next
    INDEX
    Explanations

    the word "for"

    oai_token-act-pair · gemini-2.0-flash

    verbs related to providing or delivering

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

    for

    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
     Basi
    -0.57
     itſelf
    -0.54
    they
    -0.52
     ſever
    -0.50
     faſt
    -0.50
     tunik
    -0.49
     Himself
    -0.48
    ſelves
    -0.48
    ंदीखरीदारी
    -0.48
     Sixteenth
    -0.47
    POSITIVE LOGITS
     providing
    0.74
     preparing
    0.73
     releasing
    0.71
     introducing
    0.71
     delivering
    0.71
     creating
    0.71
     implementing
    0.70
     completing
    0.69
     putting
    0.68
     promoting
    0.68
    Activations Density 2.459%

    No Known Activations