© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9707
    Prev
    Next
    INDEX
    Explanations

    words and phrases used by politicians and the media when discussing an issue and giving opinions on it.

    oai_token-act-pair · gemini-2.0-flash

    forms of "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    T
    -0.48
    E
    -0.47
    B
    -0.43
     pertenecen
    -0.43
    S
    -0.43
    K
    -0.41
    tr
    -0.41
    _
    -0.41
    opus
    -0.40
    fr
    -0.40
    POSITIVE LOGITS
    expandindo
    0.75
     Wicidata
    0.73
    verläs
    0.73
     Administrativna
    0.71
    Personensuche
    0.71
     Wikispecies
    0.71
    Manfaat
    0.70
    chappen
    0.69
     насељу
    0.69
     Савезне
    0.67
    Activations Density 2.055%

    No Known Activations