© 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. 3508
    Prev
    Next
    INDEX
    Explanations

    discourse markers showing contrast between two items

    oai_token-act-pair · gemini-2.0-flash

    say "others"

    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
     other
    -3.09
    other
    -2.78
     Other
    -2.73
    Other
    -2.66
     OTHER
    -2.52
    OTHER
    -2.30
     autres
    -2.27
     autre
    -2.14
    autres
    -2.11
    其他
    -2.06
    POSITIVE LOGITS
    WebElementEntity
    0.60
     الرياضيه
    0.60
    complexContent
    0.47
    MigrationBuilder
    0.45
     jadx
    0.43
    AndroidJUnit
    0.42
    infeld
    0.42
     المعيارى
    0.40
    hagic
    0.40
    ptonshire
    0.39
    Activations Density 4.887%

    No Known Activations