© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3224
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed", "ing" or "s"

    oai_token-act-pair · gemini-2.0-flash

    source

    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
    TagMode
    -0.84
     مرئيه
    -0.83
    GEBURTSDATUM
    -0.79
     EconPapers
    -0.78
    rungsseite
    -0.77
     FetchType
    -0.77
    ReusableCell
    -0.76
    SourceChecksum
    -0.75
     للمعارف
    -0.71
    rawDesc
    -0.70
    POSITIVE LOGITS
     source
    0.73
     Source
    0.67
    Source
    0.64
    source
    0.63
     prospect
    0.52
     outlet
    0.52
     partner
    0.52
     target
    0.50
     destination
    0.50
     victim
    0.49
    Activations Density 9.584%

    No Known Activations