© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8137
    Prev
    Next
    INDEX
    Explanations

    many common and seemingly unrelated words, perhaps indicating a failure mode

    oai_token-act-pair · 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
     encourage
    -1.81
     encouraged
    -1.79
     encouragement
    -1.78
     encouraging
    -1.74
     encourages
    -1.73
     Encourage
    -1.71
     incentive
    -1.70
     inducement
    -1.67
     invitation
    -1.64
    Encourage
    -1.64
    POSITIVE LOGITS
     financières
    0.54
    setPixel
    0.44
    Numerology
    0.43
     виправивши
    0.42
     gracilis
    0.42
     coppia
    0.41
     jsonify
    0.40
    fhir
    0.39
     ویکی‌پدیای
    0.39
    en
    0.38
    Activations Density 2.971%

    No Known Activations