© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1198
    Prev
    Next
    INDEX
    Explanations

    words, symbols, and phrases from scientific writing, especially mathematics and physics, including things like formulas with greek symbols, references, and technical terms

    oai_token-act-pair · gemini-2.0-flash

    gamma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     eigenvalue
    -0.65
     eigenvalues
    -0.57
    يكب
    -0.56
    ValueGenerated
    -0.46
    Spectral
    -0.44
    online
    -0.43
     verlei
    -0.42
    Ỏ
    -0.42
    execSQL
    -0.41
     online
    -0.41
    POSITIVE LOGITS
    iastes
    0.74
     désolés
    0.73
    });*/
    0.71
    TagHelper
    0.68
    Vidite
    0.67
    .³
    0.66
    .")]
    0.65
    存于互联网档案馆
    0.65
     nakalista
    0.65
     correctes
    0.65
    Activations Density 3.285%

    No Known Activations