© 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. 8631
    Prev
    Next
    INDEX
    Explanations

    words related to geography and locations

    oai_token-act-pair · gemini-2.0-flash

    capital

    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
    WriteTagHelper
    -0.64
    kuuta
    -0.60
    Hentet
    -0.59
    ⓧ
    -0.59
     cherchés
    -0.58
     gynhyrchwyd
    -0.53
    principalTable
    -0.51
     Allociné
    -0.48
    LEncoder
    -0.47
    Abit
    -0.47
    POSITIVE LOGITS
     capital
    2.84
     Capital
    2.44
    capital
    2.34
    Capital
    2.34
     CAPITAL
    2.31
    CAPITAL
    1.94
     capitale
    1.76
     capitals
    1.76
     capitol
    1.59
     capitalized
    1.41
    Activations Density 5.104%

    No Known Activations