© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16081
    Prev
    Next
    INDEX
    Explanations

    phrases with "be" and other auxiliary verbs, plus words relating to movie theaters, and also the phrase "isn't that".

    oai_token-act-pair · gemini-2.0-flash

    positive sentiment, explanations

    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
    tagHelperRunner
    -1.09
    SourceChecksum
    -1.02
     onCreateView
    -1.01
     cherchés
    -0.99
     للاسماء
    -0.97
    oredCriteria
    -0.96
    verwijspagina
    -0.95
    ImageContext
    -0.93
     تانيه
    -0.93
     AssemblyCulture
    -0.93
    POSITIVE LOGITS
     ver
    0.48
     Nice
    0.48
     var
    0.46
     До
    0.43
     int
    0.43
     Far
    0.42
     mest
    0.42
     Premium
    0.42
     о
    0.41
     pa
    0.41
    Activations Density 1.501%

    No Known Activations