© 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. 4540
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to experimental cell biology

    oai_token-act-pair · gemini-2.0-flash

    cell cultures and experiments

    np_max-act-logits · 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
     cultural
    -0.68
     culturelle
    -0.65
    tvguidetime
    -0.65
    cultural
    -0.64
     CULTURE
    -0.64
    Cultural
    -0.63
     Cultural
    -0.61
     Culture
    -0.61
     culturale
    -0.60
    Geplaatst
    -0.59
    POSITIVE LOGITS
    ắp
    0.56
     comp
    0.54
    ėj
    0.52
     Comp
    0.51
    fleisch
    0.50
    ėjimas
    0.49
    minecraftforge
    0.48
    ToolStrip
    0.48
     թվական
    0.48
    нике
    0.47
    Activations Density 7.057%

    No Known Activations