© 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. 7974
    Prev
    Next
    INDEX
    Explanations

    verbs describing urging, advising, campaigns and court-like systems

    oai_token-act-pair · gemini-2.0-flash

    commands and requests

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

    urging

    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
     gånger
    -0.51
     hemsida
    -0.50
     makeStyles
    -0.48
    capi
    -0.47
     privées
    -0.46
     âges
    -0.46
    чатки
    -0.44
     vagues
    -0.44
    ở
    -0.43
    埃
    -0.43
    POSITIVE LOGITS
     للمعارف
    0.77
    IsContent
    0.66
    +#+#
    0.66
     AssemblyTitle
    0.66
    +:+
    0.66
    RenderAtEndOf
    0.66
    ंदीखरीदारी
    0.62
    __':
    0.60
     merchants
    0.60
     donors
    0.60
    Activations Density 4.949%

    No Known Activations