© 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. 8995
    Prev
    Next
    INDEX
    Explanations

    words related to energy and power in technical contexts

    oai_token-act-pair · gemini-2.0-flash

    code/technical vocabulary

    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
     Power
    -3.05
    Power
    -3.00
     power
    -2.94
    power
    -2.86
     POWER
    -2.78
    POWER
    -2.72
     Powers
    -2.48
    powers
    -2.45
     powers
    -2.45
    Powers
    -2.41
    POSITIVE LOGITS
    ColumnInfo
    0.50
    Sinon
    0.49
     الاص
    0.47
    eslint
    0.46
     beraten
    0.45
     noDo
    0.43
    crivez
    0.42
    sumowanie
    0.42
     TestCase
    0.42
    äksi
    0.42
    Activations Density 2.926%

    No Known Activations