© 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. 909
    Prev
    Next
    INDEX
    Explanations

    words that are related to people, whether by name, title, or relation

    oai_token-act-pair · gemini-2.0-flash

    Quotes in news articles

    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
    rungsseite
    -1.13
    tvguidetime
    -1.05
    WriteBarrier
    -1.02
     cherchés
    -0.99
    principalTable
    -0.94
     שוליים
    -0.94
    KURZBESCHREIBUNG
    -0.91
    tagHelperRunner
    -0.91
     MainAxisSize
    -0.90
     estekak
    -0.89
    POSITIVE LOGITS
    .
    0.49
    ↵
    0.39
     
    0.36
     s
    0.35
    ​
    0.33
    ט
    0.32
    '
    0.31
    isbol
    0.30
    (
    0.29
    S
    0.28
    Activations Density 1.085%

    No Known Activations