© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14436
    Prev
    Next
    INDEX
    Explanations

    tokens surrounded by whitespace (especially newlines?) and the word "but".

    oai_token-act-pair · gemini-2.0-flash

    Carbide

    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
    ⓧ
    -0.69
    LookAnd
    -0.65
    ьаж
    -0.61
    دانشنامهٔ
    -0.59
     protoimpl
    -0.55
     lenker
    -0.53
     AssemblyCulture
    -0.52
    expandindo
    -0.50
     चीज़ों
    -0.50
    mergeFrom
    -0.49
    POSITIVE LOGITS
    SupportActionBar
    0.51
    verwijspagina
    0.47
     lyn
    0.45
     Chasse
    0.44
    paraiso
    0.44
    pinephrine
    0.44
     gneiss
    0.44
    rillation
    0.44
     pail
    0.44
    DidLoad
    0.43
    Activations Density 1.877%

    No Known Activations