© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12661
    Prev
    Next
    INDEX
    Explanations

    fragments of text from software licenses, technical specifications, and personal usage scenarios

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Without
    -1.01
    Without
    -1.00
    without
    -0.96
    WITHOUT
    -0.91
     WITHOUT
    -0.91
     without
    -0.90
     Без
    -0.88
     ohne
    -0.88
     senza
    -0.88
    senza
    -0.88
    POSITIVE LOGITS
     with
    1.46
    with
    1.14
     avec
    0.98
     With
    0.98
    With
    0.96
     WITH
    0.96
     dengan
    0.92
     với
    0.85
     wth
    0.84
     עם
    0.80
    Activations Density 2.005%

    No Known Activations