© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1289
    Prev
    Next
    INDEX
    Explanations

    a mix of both vulgar language and pronouns

    oai_token-act-pair · gemini-2.0-flash

    say "all"

    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
     All
    -2.36
    All
    -2.27
    ALL
    -2.19
     ALL
    -1.84
    all
    -1.50
     Alle
    -1.39
    Alle
    -1.34
    alle
    -1.33
    getAll
    -1.27
    alls
    -1.24
    POSITIVE LOGITS
    GenerationType
    0.52
    onaceous
    0.48
    SharedCtor
    0.47
    featureID
    0.46
    ucleotide
    0.45
    Referanser
    0.43
    thâu
    0.43
    IsMutable
    0.43
    ioneta
    0.42
    cinnati
    0.41
    Activations Density 5.111%

    No Known Activations