© 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. 9031
    Prev
    Next
    INDEX
    Explanations

    various topics like company names (KLQ, Pride Offshore, Century Exploration), locations/proper nouns (El Paso, London, England, Baltic), sports, legal jargon and numerical info

    oai_token-act-pair · gemini-2.0-flash

    top rankings and lists

    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
    expandindo
    -0.79
     Depression
    -0.70
    verwijspagina
    -0.60
    Depression
    -0.60
     beginnetje
    -0.56
    makeText
    -0.55
    rungsseite
    -0.54
    Quer
    -0.54
    Cerv
    -0.54
     Constipation
    -0.52
    POSITIVE LOGITS
    +#+#
    0.63
     BoxFit
    0.63
    RAEL
    0.56
     Record
    0.55
     propOrder
    0.54
     Rank
    0.54
     Land
    0.54
    Украина
    0.50
    antaranya
    0.50
     Ranks
    0.50
    Activations Density 6.791%

    No Known Activations