© 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. 7814
    Prev
    Next
    INDEX
    Explanations

    words related to a state of mind, or choices.

    oai_token-act-pair · gemini-2.0-flash

    prepositions and variations of "of"

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

    variations of "of"

    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
     cherchés
    -1.07
    TagHelper
    -0.99
    RenderAtEndOf
    -0.96
    ConstraintMaker
    -0.94
    ⓧ
    -0.92
    出版年
    -0.84
    enderror
    -0.84
    GEBURTSDATUM
    -0.82
    UnsafeEnabled
    -0.81
    Datuak
    -0.81
    POSITIVE LOGITS
     of
    2.19
    of
    1.03
     của
    1.02
    ของ
    0.98
     Of
    0.76
    tof
    0.73
    Of
    0.69
     OF
    0.66
     ของ
    0.66
     של
    0.65
    Activations Density 3.151%

    No Known Activations