© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6876
    Prev
    Next
    INDEX
    Explanations

    Japanese text and Java-related terms, especially those related to errors and project setup

    oai_token-act-pair · gemini-2.0-flash

    Code and file paths

    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
    ">'.$
    -0.59
     houſe
    -0.56
    tôi
    -0.55
    URDAY
    -0.54
    mặt
    -0.53
     стъ
    -0.52
     $_"
    -0.52
    ENEFITS
    -0.52
    cửa
    -0.52
    IBLIO
    -0.52
    POSITIVE LOGITS
     BoxFit
    0.66
    DockStyle
    0.59
    TagHelper
    0.55
    Parcelize
    0.52
    UnsafeEnabled
    0.52
     GenerationType
    0.51
    GeoNames
    0.51
    CloseOperation
    0.50
    **
    0.50
    enderror
    0.48
    Activations Density 0.582%

    No Known Activations