© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12796
    Prev
    Next
    INDEX
    Explanations

    hyphens followed by words related to living things and their health, as related to environmental issues.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     tongue
    -0.56
    jooq
    -0.53
    RTLD
    -0.52
    LookAnd
    -0.51
     snowball
    -0.51
     apothe
    -0.51
     cloak
    -0.50
    setVerticalGroup
    -0.48
     telescopes
    -0.47
     molasses
    -0.47
    POSITIVE LOGITS
    towym
    0.60
     automatiques
    0.59
     dignité
    0.57
     spéciaux
    0.56
     pungkas
    0.55
    Ligações
    0.55
     fédé
    0.54
     enviado
    0.54
     télécharge
    0.54
     réguli
    0.54
    Activations Density 7.503%

    No Known Activations