© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12827
    Prev
    Next
    INDEX
    Explanations

    a mix of terms related to science and health

    oai_token-act-pair · gemini-2.0-flash

    Code/technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     becomes
    -0.72
    Brainz
    -0.69
     begins
    -0.69
     commences
    -0.68
     gets
    -0.66
    begins
    -0.65
    είς
    -0.63
    Personendaten
    -0.63
    Географи
    -0.62
    TokenNameLBRACE
    -0.62
    POSITIVE LOGITS
     seam
    0.46
    ilt
    0.41
     bil
    0.41
     binh
    0.40
    ultati
    0.40
    ViewFeatures
    0.39
    ::{
    0.39
    dol
    0.39
    databinding
    0.39
    民
    0.37
    Activations Density 2.912%

    No Known Activations