© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2630
    Prev
    Next
    INDEX
    Explanations

    terms related to machine learning algorithms and processes, especially random forests and their application in data analysis

    oai_token-act-pair · gemini-2.0-flash

    forest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Offisielt
    -0.60
     AssemblyCulture
    -0.59
     Bili
    -0.58
    าศ
    -0.54
     Stretcher
    -0.54
    TemporalType
    -0.53
    maß
    -0.52
     appré
    -0.52
    φό
    -0.52
    Демографія
    -0.52
    POSITIVE LOGITS
    <bos>
    1.03
    jface
    0.68
     []:
    0.60
    openzeppelin
    0.56
    SBATCH
    0.54
    providedIn
    0.51
     chatbot
    0.50
     OMITBAD
    0.48
    onAttach
    0.48
    اریخ
    0.47
    Activations Density 2.225%

    No Known Activations