© 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. 5394
    Prev
    Next
    INDEX
    Explanations

    Japanese words related to errors and building software.

    oai_token-act-pair · gemini-2.0-flash

    Code and Japanese text

    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
     engraçadas
    -0.74
     femininas
    -0.69
     réguli
    -0.69
     électroniques
    -0.69
     âgées
    -0.68
     vermelhas
    -0.67
     définiti
    -0.66
     brancas
    -0.65
     sauvages
    -0.63
     normaux
    -0.63
    POSITIVE LOGITS
    ADORES
    0.54
     naselje
    0.52
     SwitchCompat
    0.51
    ERÍA
    0.50
    )"),
    0.48
    ARIOS
    0.48
    település
    0.48
    saurus
    0.47
    XmlEnum
    0.47
    ADOS
    0.46
    Activations Density 0.091%

    No Known Activations