© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3700
    Prev
    Next
    INDEX
    Explanations

    scientific publication references

    oai_token-act-pair · gemini-2.0-flash

    academic URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    -
    -0.40
     él
    -0.39
    t
    -0.36
     jadx
    -0.36
    <strong>
    -0.36
     $
    -0.35
     belang
    -0.35
    S
    -0.35
     quedó
    -0.34
    hmi
    -0.34
    POSITIVE LOGITS
    NameInMap
    0.91
     snippetHide
    0.89
    <()>
    0.88
    RenderAtEndOf
    0.88
    UnsafeEnabled
    0.78
    Personendaten
    0.78
    IntoConstraints
    0.77
    Hentet
    0.76
    ArgumentParser
    0.76
    sizeCache
    0.74
    Activations Density 1.785%

    No Known Activations