© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3818
    Prev
    Next
    INDEX
    Explanations

    code or code-like language, along with the topic of algebra

    oai_token-act-pair · gemini-2.0-flash

    Source code/Math

    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
    principalColumn
    -0.77
    IntoConstraints
    -0.71
    IndentedString
    -0.71
    GOTREF
    -0.60
    Initializable
    -0.59
    MENAFN
    -0.59
    oredCriteria
    -0.58
    saraba
    -0.57
     Efq
    -0.55
    GEBURTSDATUM
    -0.54
    POSITIVE LOGITS
    GHIJKLM
    0.50
    Shea
    0.49
    czaj
    0.48
    Portail
    0.47
    TODO
    0.46
    hower
    0.46
    ambi
    0.45
    izer
    0.44
     Commune
    0.44
    Mie
    0.44
    Activations Density 2.216%

    No Known Activations