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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14788
    Prev
    Next
    INDEX
    Explanations

    words related to the Italian language, science fiction, legal documents, and electrons

    oai_token-act-pair · gemini-2.0-flash

    foreign text snippets

    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
    DeleteBehavior
    -0.78
    tanleria
    -0.54
    PerformLayout
    -0.49
     annuelle
    -0.48
    contentLoaded
    -0.46
     tilgjenge
    -0.46
    IndentedString
    -0.45
    fromnode
    -0.45
     bezeichneter
    -0.44
    Personensuche
    -0.44
    POSITIVE LOGITS
     يتيمه
    0.65
     Monfieur
    0.59
    abbaye
    0.58
     Theſe
    0.58
    ✭
    0.58
    NamedQueries
    0.57
     ſeveral
    0.54
     lamin
    0.54
     useStyles
    0.53
     Diſ
    0.53
    Activations Density 0.536%

    No Known Activations