© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5938
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SharedCtor
    -0.52
    DataMember
    -0.44
     mérito
    -0.44
    existsSync
    -0.44
     festive
    -0.42
    christmas
    -0.42
    Stap
    -0.41
     anteriores
    -0.40
    üstü
    -0.40
     opérés
    -0.40
    POSITIVE LOGITS
    Geplaatst
    0.85
    ValueStyle
    0.76
     nakalista
    0.74
    InputBorder
    0.69
    RegressionTest
    0.68
    TagHelper
    0.66
     Италијани
    0.63
    "]))
    0.62
    :✨
    0.60
    @[+][
    0.58
    Activations Density 0.385%

    No Known Activations