© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12947
    Prev
    Next
    INDEX
    Explanations

    positive or useful attributes of something.

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

    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
    ніципа
    -0.90
    AndroidJUnit
    -0.80
    GEBURTSDATUM
    -0.74
    UnitTesting
    -0.74
     AssemblyVersion
    -0.74
    Personendaten
    -0.73
    LabelTagHelper
    -0.73
     trajets
    -0.73
    UnknownFieldSet
    -0.72
    extAlignment
    -0.72
    POSITIVE LOGITS
    tagext
    0.36
    Външни
    0.35
    dafri
    0.35
     comerciales
    0.35
     commercial
    0.35
    merci
    0.35
     cuales
    0.33
     Dostupné
    0.33
    Voyage
    0.33
    tagHelper
    0.32
    Activations Density 21.947%

    No Known Activations