© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4715
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation

    oai_token-act-pair · gemini-2.0-flash

    frac

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     nahilalakip
    -0.92
    Personensuche
    -0.86
    InitVars
    -0.85
     незавершена
    -0.84
     >=",
    -0.83
    EDEFAULT
    -0.82
     disambiguazione
    -0.81
    يكب
    -0.79
    NameInMap
    -0.75
     betweenstory
    -0.74
    POSITIVE LOGITS
     zich
    0.42
    oso
    0.41
     impl
    0.40
    esc
    0.40
    frac
    0.39
     ado
    0.39
    dojo
    0.39
     National
    0.39
     expressed
    0.39
     #
    0.38
    Activations Density 2.077%

    No Known Activations