© 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. 7985
    Prev
    Next
    INDEX
    Explanations

    transitions between negative and positive sentiment

    oai_token-act-pair · gemini-2.0-flash

    quantity and amount

    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
     much
    -2.81
    much
    -2.73
    Much
    -2.72
     Much
    -2.58
     MUCH
    -2.16
     mucho
    -1.84
    mucho
    -1.66
     viel
    -1.52
     paljon
    -1.41
     beaucoup
    -1.39
    POSITIVE LOGITS
    ario
    0.35
    atan
    0.33
    ision
    0.30
    liy
    0.30
    ior
    0.29
    atu
    0.29
     Small
    0.29
    ure
    0.29
    от
    0.29
    set
    0.28
    Activations Density 9.152%

    No Known Activations