© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13307
    Prev
    Next
    INDEX
    Explanations

    technical language about diluting samples and conducting tests, particularly in antibody-related studies described in the context of lab procedures

    oai_token-act-pair · gemini-2.0-flash

    ratios

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    RegistryLite
    -0.70
    Portail
    -0.70
    __':
    -0.69
    rungsseite
    -0.68
    __':
    -0.66
     tartalomajánló
    -0.64
     Trench
    -0.63
     StringTokenizer
    -0.63
    __":
    -0.62
     تانيه
    -0.61
    POSITIVE LOGITS
     ratio
    0.75
    ratio
    0.71
     One
    0.63
     Ratio
    0.61
     ratios
    0.60
    Ratio
    0.59
    ratios
    0.57
     propor
    0.55
     many
    0.55
    One
    0.54
    Activations Density 1.447%

    No Known Activations