© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12085
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those related to Android or Gradle projects

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    DoubleQuotes
    -0.58
    FieldNumber
    -0.52
    ResumeLayout
    -0.52
    ReusableCell
    -0.52
    matchCondition
    -0.48
    Teraz
    -0.48
    Parcelize
    -0.48
    存于互联网档案馆
    -0.47
    IntoConstraints
    -0.47
    usermodel
    -0.43
    POSITIVE LOGITS
    principalTable
    0.62
    ğraf
    0.60
    ņi
    0.59
    StoryboardSegue
    0.56
    signor
    0.55
    angulaire
    0.55
    atyana
    0.55
    PhysRev
    0.55
     Haushalt
    0.53
     Mong
    0.52
    Activations Density 2.347%

    No Known Activations