© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12120
    Prev
    Next
    INDEX
    Explanations

    technical documents describing blood pressure and cyber security issues

    oai_token-act-pair · gemini-2.0-flash

    words related to blood

    np_token-act-pair-logits · gpt-4o-mini

    blood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Seel
    -0.42
     Sunscreen
    -0.41
     trạng
    -0.41
     regra
    -0.40
    infeld
    -0.40
    ACM
    -0.40
     pág
    -0.39
    siella
    -0.39
     civiles
    -0.39
    annelse
    -0.38
    POSITIVE LOGITS
     blood
    1.69
     Blood
    1.51
    Blood
    1.44
    blood
    1.43
     BLOOD
    1.38
    BLOOD
    1.22
    血
    1.10
     Blut
    1.09
     blod
    1.08
     darah
    1.03
    Activations Density 2.326%

    No Known Activations