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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7639
    Prev
    Next
    INDEX
    Explanations

    a wide range of common words, question words and pronouns, plus words relating to the camera, energy, firefighting, and boiler malfunction

    oai_token-act-pair · gemini-2.0-flash

    light

    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
    Slf
    -0.46
    Loud
    -0.45
    __':
    -0.45
    SuppressLint
    -0.44
    addLast
    -0.43
    ableness
    -0.43
    assertRaises
    -0.42
    loud
    -0.41
     seg
    -0.41
     Kass
    -0.41
    POSITIVE LOGITS
     light
    2.75
     Light
    2.34
    light
    2.34
    Light
    2.30
     LIGHT
    1.81
    LIGHT
    1.70
     licht
    1.30
     lighter
    1.24
     luz
    1.15
     lumière
    1.14
    Activations Density 5.705%

    No Known Activations