© 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. 16050
    Prev
    Next
    INDEX
    Explanations

    words related to government regulations and bureaucracy

    oai_token-act-pair · gemini-2.0-flash

    Rules, regulations, and policies

    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
    enumi
    -0.80
     виправивши
    -0.72
     Normdatei
    -0.71
    djangoproject
    -0.70
    AddTagHelper
    -0.68
     صوتيه
    -0.68
    twimg
    -0.67
    Personensuche
    -0.66
    ValueStyle
    -0.66
    principalColumn
    -0.65
    POSITIVE LOGITS
     ModelExpression
    0.55
     dead
    0.43
     aceptas
    0.42
     propOrder
    0.42
    Ac
    0.41
    ards
    0.41
     po
    0.41
     complic
    0.41
    AC
    0.40
     mempel
    0.40
    Activations Density 1.834%

    No Known Activations