© 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. 4208
    Prev
    Next
    INDEX
    Explanations

    words related to cooking with a focus on drinks

    oai_token-act-pair · gemini-2.0-flash

    liquids and powders

    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
     nahilalakip
    -0.90
     tartalomajánló
    -0.84
    tvguidetime
    -0.83
    Билгалдахарш
    -0.79
     esternos
    -0.73
    ThroughAttribute
    -0.73
    featureID
    -0.71
    SerializedSize
    -0.69
     &___
    -0.69
    HasForeignKey
    -0.68
    POSITIVE LOGITS
     Verw
    0.47
     thinned
    0.45
     fidd
    0.45
     mixed
    0.44
     slurry
    0.43
     Ald
    0.43
    igold
    0.43
     Kap
    0.43
     heavily
    0.42
     Concentrate
    0.42
    Activations Density 10.385%

    No Known Activations