© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3146
    Prev
    Next
    INDEX
    Explanations

    references to specific politicians or political parties

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'vote'

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

    Voting

    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
     autorytatywna
    -0.72
     linkovi
    -0.53
    MockBean
    -0.52
    webElementXpaths
    -0.48
    ⓧ
    -0.47
     Nachdem
    -0.47
    ]:
    -0.44
    "?>
    -0.43
     بيها
    -0.43
    Aktualisiert
    -0.42
    POSITIVE LOGITS
     voting
    1.11
     Voting
    0.94
     votes
    0.94
     voted
    0.93
     vote
    0.91
    Voting
    0.84
    voting
    0.84
    vote
    0.82
     Vote
    0.81
     Voted
    0.78
    Activations Density 2.854%

    No Known Activations