© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4191
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    oai_token-act-pair · gemini-2.0-flash

    ordinal suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.90
    Th
    -0.59
     />";
    -0.54
     Basta
    -0.54
    Personensuche
    -0.53
     EconPapers
    -0.52
     gesso
    -0.52
     />';
    -0.52
     Th
    -0.51
     переписи
    -0.51
    POSITIVE LOGITS
     third
    1.35
     second
    1.30
     fifth
    1.29
     fourth
    1.28
     sixth
    1.25
     Second
    1.23
     THIRD
    1.20
    third
    1.19
    fifth
    1.19
     SECOND
    1.18
    Activations Density 1.560%

    No Known Activations