© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15400
    Prev
    Next
    INDEX
    Explanations

    proper nouns for places, people and organizations

    oai_token-act-pair · gemini-2.0-flash

    location

    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
    LEGGI
    -0.60
     léč
    -0.46
     Myself
    -0.43
    Desired
    -0.42
     Maier
    -0.42
     direta
    -0.42
    ForRow
    -0.41
     frattempo
    -0.41
     adapts
    -0.41
     Triple
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    1.02
    GEBURTSDATUM
    0.97
    ArrowToggle
    0.93
    richTextPanel
    0.81
    nonatomic
    0.75
     otomatig
    0.75
    enumi
    0.72
     utafitiHapana
    0.72
    NameInMap
    0.71
     defaultstate
    0.71
    Activations Density 1.858%

    No Known Activations