© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12765
    Prev
    Next
    INDEX
    Explanations

    words associated with mathematical and physics equations and theorems

    oai_token-act-pair · gemini-2.0-flash

    Scientific notations and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.56
    fonos
    -0.50
    országban
    -0.48
    Ớ
    -0.48
    anias
    -0.45
    ודי
    -0.45
     retour
    -0.44
     all
    -0.44
     ју
    -0.43
    FormTagHelper
    -0.43
    POSITIVE LOGITS
    \{\\
    0.71
    enderror
    0.64
     مشين
    0.64
    Rhestr
    0.61
     BoxFit
    0.60
    MemoryWarning
    0.57
     onAnimation
    0.55
    Према
    0.55
     doInBackground
    0.53
     nahilalakip
    0.53
    Activations Density 2.693%

    No Known Activations