© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14775
    Prev
    Next
    INDEX
    Explanations

    words associated with the music industry

    oai_token-act-pair · gemini-2.0-flash

    independent and local artists

    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
    ContentAsync
    -0.66
     Major
    -0.61
     referrerpolicy
    -0.58
    EndContext
    -0.58
    Major
    -0.54
    demic
    -0.54
    tichetta
    -0.54
    ReusableCell
    -0.53
     Majors
    -0.53
    enumi
    -0.52
    POSITIVE LOGITS
     ویکی‌پدیا
    0.66
    IndentedString
    0.62
     betweenstory
    0.60
    expandindo
    0.57
    XmlAccessType
    0.54
    Kjelder
    0.48
     sumpay
    0.48
    addCriterion
    0.47
    Билгалдахарш
    0.46
    richTextPanel
    0.46
    Activations Density 10.073%

    No Known Activations