© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11682
    Prev
    Next
    INDEX
    Explanations

    sentences about crime and law enforcement

    oai_token-act-pair · gemini-2.0-flash

    crime and drug possession

    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
     مشين
    -0.63
    GraphicsUnit
    -0.62
     ProtoMessage
    -0.59
    Искәрмәләр
    -0.59
    IntoConstraints
    -0.56
    CloseOperation
    -0.51
     Tenta
    -0.51
    BorderFactory
    -0.50
     responsible
    -0.50
     accountable
    -0.50
    POSITIVE LOGITS
     térmica
    0.49
    JsonHelper
    0.47
     старости
    0.47
     uchiha
    0.47
    NOPQRST
    0.46
    Història
    0.46
     depends
    0.45
    bidi
    0.45
    InstanceState
    0.45
    netje
    0.45
    Activations Density 3.472%

    No Known Activations