© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11065
    Prev
    Next
    INDEX
    Explanations

    words that are related to computers or software engineering, particularly around account configuration

    oai_token-act-pair · gemini-2.0-flash

    accounting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    MeasureSpec
    -0.67
    <bos>
    -0.55
    ThemeOverlay
    -0.52
    SBATCH
    -0.52
    veria
    -0.50
     собой
    -0.49
     colectiva
    -0.49
    IST
    -0.49
    openzeppelin
    -0.47
     createState
    -0.46
    POSITIVE LOGITS
    Personensuche
    0.69
    #
    0.68
    onViewCreated
    0.65
    abestanden
    0.58
    RTEE
    0.56
     المرجع
    0.56
    yntaxException
    0.55
    ksikon
    0.55
    thâu
    0.55
    WithMany
    0.54
    Activations Density 0.834%

    No Known Activations