© 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. 9295
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures, inventors, or founders of companies and recognizes the context of creation, invention and foundation

    oai_token-act-pair · gemini-2.0-flash

    Inventions and founders

    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
     founding
    -0.64
    Diweddarwch
    -0.57
    SharedCtor
    -0.55
     localObject
    -0.54
    DebuggerNonUser
    -0.54
    TabIndex
    -0.54
    didSet
    -0.54
    ImageContext
    -0.54
     Vainqueur
    -0.53
     Founding
    -0.52
    POSITIVE LOGITS
    politan
    0.58
     Hand
    0.57
    Hand
    0.55
     runs
    0.54
     HAND
    0.54
    hånd
    0.53
    runs
    0.51
     Runs
    0.51
    itzenden
    0.50
    HasAnnotation
    0.49
    Activations Density 5.682%

    No Known Activations