© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11358
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to political elections, races, wins and losses

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    losses and defeats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     winning
    -2.19
     win
    -2.16
     wins
    -2.00
     winner
    -1.85
     Winning
    -1.84
    Winning
    -1.84
    winning
    -1.80
    win
    -1.80
     winners
    -1.77
     Win
    -1.66
    POSITIVE LOGITS
     &___
    0.59
    ieteur
    0.53
     NgModule
    0.52
     кӀош
    0.52
     trás
    0.52
     LiveData
    0.51
    philis
    0.49
    ̣
    0.48
    uding
    0.48
    }]);
    0.48
    Activations Density 1.463%

    No Known Activations