© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9389
    Prev
    Next
    INDEX
    Explanations

    proper nouns including locations, people, organizations, and more

    oai_token-act-pair · gemini-2.0-flash

    cities

    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
     createState
    -0.53
    ensi
    -0.44
     pang
    -0.44
     hào
    -0.43
     flashback
    -0.43
    صف
    -0.42
    FirebaseDatabase
    -0.42
     ado
    -0.41
    createCanvas
    -0.41
    aVar
    -0.41
    POSITIVE LOGITS
    TypedDataSet
    0.79
    IsContent
    0.73
    Попис
    0.71
    featureID
    0.67
    ArrowToggle
    0.63
    IndentedString
    0.61
     الرياضيه
    0.60
    AndEndTag
    0.60
    Gön
    0.60
    帖最后由
    0.60
    Activations Density 6.943%

    No Known Activations