© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3898
    Prev
    Next
    INDEX
    Explanations

    commas, conjunctions, and certain pronouns in the context of complex technical writing

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     незавершена
    -0.67
     oprot
    -0.66
    Hauptartikel
    -0.61
    RegressionTest
    -0.61
     @"/
    -0.60
    :][
    -0.57
     Réponses
    -0.56
    ).]
    -0.54
    cahontas
    -0.54
    évaluateur
    -0.54
    POSITIVE LOGITS
     /\.
    0.52
    orgung
    0.49
    AttributeSet
    0.48
    ubehör
    0.46
    DispatchToProps
    0.45
    thető
    0.45
     generales
    0.44
     réglable
    0.43
    MIDDLEWARE
    0.43
     Overall
    0.43
    Activations Density 1.240%

    No Known Activations