© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13786
    Prev
    Next
    INDEX
    Explanations

    mentions of being on a board of directors or committee and related concepts

    oai_token-act-pair · gemini-2.0-flash

    committees, boards, councils

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IsContent
    -0.82
    rawDesc
    -0.81
     للمعارف
    -0.65
    XmlAccessType
    -0.64
    chair
    -0.63
    Espèce
    -0.63
     ""],
    -0.61
    MessageOf
    -0.61
    Chair
    -0.61
    Transcription
    -0.61
    POSITIVE LOGITS
     Mur
    0.52
    ่าย
    0.44
    ัว
    0.43
    RegistryLite
    0.43
     شم
    0.42
    hamel
    0.42
    giver
    0.42
    Mur
    0.41
    glBindTexture
    0.41
     LCCN
    0.40
    Activations Density 2.841%

    No Known Activations