© 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. 6322
    Prev
    Next
    INDEX
    Explanations

    mentions of political oppression or persecution

    oai_token-act-pair · gemini-2.0-flash

    Political activism/oppression

    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
    contentLoaded
    -0.78
    __":
    -0.73
    __":
    -0.63
    httphttps
    -0.63
    LookAnd
    -0.61
     nahilalakip
    -0.60
    __':
    -0.60
    exitRule
    -0.60
    adpleegd
    -0.60
    onAttach
    -0.59
    POSITIVE LOGITS
    Zeneca
    0.52
    tily
    0.45
    δη
    0.45
     <<<<<<<<<<<<<<
    0.45
    Pageable
    0.45
    ライト
    0.44
     Magn
    0.44
    Scope
    0.44
    Nib
    0.44
    formatics
    0.43
    Activations Density 3.377%

    No Known Activations