© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5881
    Prev
    Next
    INDEX
    Explanations

    language related to verbal conflict, legal proceedings or political campaigns

    oai_token-act-pair · gemini-2.0-flash

    conflict and debate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     kasarigan
    -0.69
     صوتيه
    -0.66
    webElementXpaths
    -0.63
    IUrlHelper
    -0.56
     referenties
    -0.55
     GenerationType
    -0.55
     esternos
    -0.55
    Aiheesta
    -0.54
    Autoritní
    -0.54
    Datuak
    -0.53
    POSITIVE LOGITS
     finger
    0.65
     tau
    0.59
     sne
    0.56
     je
    0.56
    jec
    0.55
     name
    0.53
     shouts
    0.52
     hu
    0.51
    gant
    0.51
     pointed
    0.50
    Activations Density 4.082%

    No Known Activations