© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5568
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and processes as well as associated sentiment

    oai_token-act-pair · gemini-2.0-flash

    politics and public opinion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     '\\;'
    -0.74
     defaultstate
    -0.60
    qrstuvwxyz
    -0.57
    TintMode
    -0.57
    uxxxx
    -0.57
    
    -0.57
    LEncoder
    -0.56
    ResumeLayout
    -0.54
    Produzione
    -0.54
     Phari
    -0.53
    POSITIVE LOGITS
     trust
    0.49
    ]-->
    0.47
    Референце
    0.46
    trust
    0.46
    getFullYear
    0.45
    يبة
    0.44
    Equivalent
    0.44
    Gweler
    0.43
    Steg
    0.41
    Major
    0.41
    Activations Density 5.297%

    No Known Activations