© 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. 13916
    Prev
    Next
    INDEX
    Explanations

    academics discussing feature selection, analysis and prediction for computer related topics

    oai_token-act-pair · gemini-2.0-flash

    Data science papers

    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
    ddots
    -0.52
    saraba
    -0.49
     kaynağından
    -0.48
    espé
    -0.48
    اعمال
    -0.48
     astore
    -0.47
    Selections
    -0.47
    -------
    -0.46
    FORMA
    -0.46
    maus
    -0.45
    POSITIVE LOGITS
     utafitiHapana
    0.71
    MemoryWarning
    0.70
     виправивши
    0.68
    WriteTagHelper
    0.67
    NewUrlParser
    0.61
    ImageContext
    0.60
    دانشنامهٔ
    0.60
    IonicModule
    0.59
     Normdatei
    0.57
    Personendaten
    0.57
    Activations Density 7.882%

    No Known Activations