© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2566
    Prev
    Next
    INDEX
    Explanations

    text related to business strategy or construction market conditions

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
     statis
    -0.51
    HomeAsUpEnabled
    -0.51
     Statistik
    -0.51
     Insight
    -0.50
     Statistics
    -0.50
    Insight
    -0.49
    ENGER
    -0.48
    統計
    -0.48
    utnant
    -0.47
    notic
    -0.47
    POSITIVE LOGITS
     ویکی‌پدیای
    0.60
    EditorBrowsable
    0.59
     MonoBehaviour
    0.58
    writeFieldEnd
    0.58
    Gön
    0.56
    ########.
    0.55
     transfé
    0.55
    دانشنامهٔ
    0.54
    úsqueda
    0.53
    zont
    0.52
    Activations Density 14.691%

    No Known Activations