© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8598
    Prev
    Next
    INDEX
    Explanations

    words related to performing arts and the people who perform them, especially in acting and films.

    oai_token-act-pair · gemini-2.0-flash

    Movies and television

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ']))
    
    -0.57
    Diweddarwch
    -0.55
     useRef
    -0.52
    庁
    -0.52
    ']],
    -0.50
    Климат
    -0.49
     <=",
    -0.48
    はじめに
    -0.48
     "..\..\
    -0.48
    Serial
    -0.47
    POSITIVE LOGITS
    oredCriteria
    0.53
    NewRow
    0.52
    Brainz
    0.51
    principalColumn
    0.51
     Bubbles
    0.50
     vulgaires
    0.50
    scalatest
    0.49
    prozess
    0.48
    bulin
    0.48
    ebenarnya
    0.48
    Activations Density 4.846%

    No Known Activations