© 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. 13746
    Prev
    Next
    INDEX
    Explanations

    family members and numbers

    oai_token-act-pair · gemini-2.0-flash

    terms related to family and relationships

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

    family members and numbers

    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
     two
    -0.59
     Trouver
    -0.55
     an
    -0.51
     dele
    -0.48
     colspan
    -0.48
    ^[
    -0.47
     four
    -0.47
     deux
    -0.46
    time
    -0.45
    ovka
    -0.45
    POSITIVE LOGITS
     فريبيس
    0.73
     المعيارى
    0.72
     виправивши
    0.66
    ########.
    0.59
     Administrativna
    0.58
     Audiodateien
    0.57
    uesia
    0.55
    DockStyle
    0.53
    enumii
    0.53
     entanto
    0.53
    Activations Density 0.389%

    No Known Activations