© 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. 2191
    Prev
    Next
    INDEX
    Explanations

    phrases in all caps asserting that having a purpose leads to clear thinking and happiness, alongside related words that might hint that the topic is quantum physics

    oai_token-act-pair · gemini-2.0-flash

    Code/technical documentation

    np_max-act-logits · 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
    ME
    -0.56
     ME
    -0.55
     M
    -0.45
    M
    -0.44
    MENAFN
    -0.43
    ím
    -0.43
    EME
    -0.42
    imir
    -0.42
    otte
    -0.41
    MEP
    -0.40
    POSITIVE LOGITS
    AddTagHelper
    0.70
    TagMode
    0.69
    Geplaatst
    0.68
    keyColumn
    0.67
     CA
    0.66
    rrggbb
    0.66
     PH
    0.65
    EndGlobalSection
    0.65
    ForValue
    0.63
     ExecuteAsync
    0.60
    Activations Density 1.505%

    No Known Activations