© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8690
    Prev
    Next
    INDEX
    Explanations

    greetings followed by names and polite words.

    oai_token-act-pair · 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
    AsUp
    -0.56
     laiko
    -0.53
    Czytaj
    -0.51
    =?";
    -0.51
    PerformLayout
    -0.51
    endimiento
    -0.50
     Kün
    -0.50
    mounting
    -0.50
    aerial
    -0.49
     seated
    -0.49
    POSITIVE LOGITS
     الرياضيه
    0.70
    IntoConstraints
    0.69
    ConstraintMaker
    0.67
    Personensuche
    0.66
    AccessorTable
    0.55
    bootstrapcdn
    0.54
    دانشنامهٔ
    0.54
     useRouter
    0.54
     jadx
    0.52
     pinulongan
    0.52
    Activations Density 27.429%

    No Known Activations