© 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. 1913
    Prev
    Next
    INDEX
    Explanations

    text from a person talking to another person or describing a person

    oai_token-act-pair · gemini-2.0-flash

    rock or rule

    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
    hartt
    -0.52
     kaarangay
    -0.52
    WebElementEntity
    -0.50
     cuivre
    -0.49
     OMIT
    -0.47
     AQUÍ
    -0.46
    BASEPATH
    -0.46
    Vidite
    -0.45
    তথ্যসূত্র
    -0.45
    Espèce
    -0.44
    POSITIVE LOGITS
     rock
    1.57
     rocks
    1.52
     Rock
    1.50
     rule
    1.48
     ROCK
    1.41
    rock
    1.41
    Rock
    1.36
     Rule
    1.33
     Rocks
    1.33
    rule
    1.31
    Activations Density 3.306%

    No Known Activations