© 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. 12753
    Prev
    Next
    INDEX
    Explanations

    language associated with tracking numbers, or following numerical trends

    oai_token-act-pair · gemini-2.0-flash

    has

    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
     elettrico
    -0.54
     Leland
    -0.52
     smtplib
    -0.52
    Carriera
    -0.49
    urlopen
    -0.48
     plastica
    -0.47
     Luch
    -0.47
     frattempo
    -0.46
     élas
    -0.46
     creciendo
    -0.45
    POSITIVE LOGITS
    ReusableCell
    0.65
     relâche
    0.62
    NOPQRST
    0.61
     Chwiliwch
    0.59
    ContentAlignment
    0.56
     BoxFit
    0.55
     ComVisible
    0.55
     LUMP
    0.54
    ksikon
    0.54
     margin
    0.52
    Activations Density 1.505%

    No Known Activations