© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11742
    Prev
    Next
    INDEX
    Explanations

    technical descriptions along with data pertaining to research and engineering

    oai_token-act-pair · gemini-2.0-flash

    Scientific/Technical texts

    np_max-act-logits · gemini-2.0-flash

    that

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Efq
    -0.54
     autorytatywna
    -0.51
    ^(@)
    -0.50
     myſelf
    -0.49
     nahilalakip
    -0.48
     Majefty
    -0.48
     ſeveral
    -0.47
    tanleria
    -0.47
    RenderAtEndOf
    -0.47
    MigrationBuilder
    -0.46
    POSITIVE LOGITS
    <bos>
    0.75
    mo
    0.31
    vor
    0.30
    jo
    0.30
     F
    0.30
    ino
    0.30
    lo
    0.30
    w
    0.30
    ma
    0.30
     f
    0.29
    Activations Density 58.741%

    No Known Activations