© 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. 7716
    Prev
    Next
    INDEX
    Explanations

    the word "government" and words related to politics

    oai_token-act-pair · gemini-2.0-flash

    terms related to government

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

    government

    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
     TAMBÉM
    -0.60
     الرياضيه
    -0.47
     dépôt
    -0.46
     ruote
    -0.46
    hunt
    -0.46
     récupération
    -0.45
     retrait
    -0.44
     corações
    -0.44
     alté
    -0.44
     vôtre
    -0.44
    POSITIVE LOGITS
     nakalista
    0.87
     autorytatywna
    0.73
     AssemblyCompany
    0.71
    DIPSETTING
    0.70
    SizeMode
    0.68
     mapStateToProps
    0.63
    SPONSORED
    0.62
     PARSER
    0.61
    Xna
    0.60
    MIDDLEWARE
    0.59
    Activations Density 3.012%

    No Known Activations