© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6961
    Prev
    Next
    INDEX
    Explanations

    references to countries, continents, or geopolitical regions, alongside associated political terminology and statistics.

    oai_token-act-pair · gemini-2.0-flash

    countries

    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
    -0.71
    ChildScrollView
    -0.56
    oredCriteria
    -0.54
    SPATH
    -0.50
    offsetof
    -0.49
    enumii
    -0.49
    stateProvider
    -0.47
    UnusedPrivate
    -0.47
    ]")]
    -0.46
    cookieParser
    -0.46
    POSITIVE LOGITS
     faces
    0.78
     face
    0.64
    faces
    0.60
     is
    0.59
     MotionEvent
    0.58
     remains
    0.55
     faced
    0.54
     hangs
    0.54
     confronts
    0.54
    iented
    0.54
    Activations Density 2.596%

    No Known Activations