© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11548
    Prev
    Next
    INDEX
    Explanations

    words related to mythical battles and realms including words such as king, world, heaven, fairy, and seal

    oai_token-act-pair · gemini-2.0-flash

    overcoming obstacles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     pleaſure
    -0.68
     Monfieur
    -0.65
     quæ
    -0.62
     ſeveral
    -0.61
     sguardo
    -0.60
     ſever
    -0.57
     créativité
    -0.56
     Theſe
    -0.56
     tuyo
    -0.56
     mío
    -0.56
    POSITIVE LOGITS
    MemoryWarning
    0.68
    WriteBarrier
    0.58
     BoxFit
    0.53
    ikyuu
    0.53
    FormTagHelper
    0.53
    viewDidLoad
    0.50
    medim
    0.50
    /)
    0.50
     Cris
    0.48
    ubernur
    0.47
    Activations Density 1.011%

    No Known Activations