© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4183
    Prev
    Next
    INDEX
    Explanations

    location and funding information

    oai_token-act-pair · gemini-2.0-flash

    academic/legal texts

    np_max-act-logits · gemini-2.0-flash
    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
    w
    -0.43
     dealt
    -0.38
    com
    -0.36
     a
    -0.35
    Die
    -0.35
    ker
    -0.35
     me
    -0.34
    تش
    -0.34
    Dealing
    -0.34
    v
    -0.34
    POSITIVE LOGITS
     سكانية
    1.04
    MLLoader
    0.95
     InputDecoration
    0.94
     Roskov
    0.92
     propOrder
    0.88
    بوابة
    0.84
     nahilalakip
    0.83
    MigrationBuilder
    0.82
    OGND
    0.81
    abestanden
    0.78
    Activations Density 1.027%

    No Known Activations