© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5847
    Prev
    Next
    INDEX
    Explanations

    XML code and android-related terms, or programming code in general

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    e
    -0.50
    i
    -0.49
    atology
    -0.49
    2
    -0.47
    a
    -0.46
     written
    -0.46
    By
    -0.46
    face
    -0.45
    [toxicity=0]
    -0.44
    b
    -0.44
    POSITIVE LOGITS
    matchCondition
    0.85
    principalColumn
    0.81
    StructEnd
    0.80
    hoeddwyd
    0.78
    "],
    0.78
    Хьажоргаш
    0.76
    migrationBuilder
    0.72
    ]),
    0.72
     snippetHide
    0.72
    httphttps
    0.71
    Activations Density 0.460%

    No Known Activations