© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6622
    Prev
    Next
    INDEX
    Explanations

    phrases about economic and social struggle including being forced to take action, family needs, and government action

    oai_token-act-pair · gemini-2.0-flash

    Survive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    \{\\
    -0.72
    rigkeit
    -0.69
     Tahu
    -0.63
    BeginContext
    -0.61
    мум
    -0.60
    +#+
    -0.57
    клопе
    -0.57
    ณา
    -0.56
    MHC
    -0.56
     awarding
    -0.55
    POSITIVE LOGITS
     Survi
    0.93
     survival
    0.92
     survived
    0.90
     survive
    0.87
     SURV
    0.85
     survives
    0.84
    Survi
    0.82
    Surviving
    0.79
     Survival
    0.75
     sobrevi
    0.75
    Activations Density 0.749%

    No Known Activations