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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7452
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and words with legal associations

    oai_token-act-pair · gemini-2.0-flash

    Narratives and stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     BoxDecoration
    -0.59
     LoginComponent
    -0.59
    built
    -0.47
    akala
    -0.44
     CHtml
    -0.44
    bought
    -0.43
     acquired
    -0.43
     crystallized
    -0.43
     imprimée
    -0.43
     Learned
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.67
    InitVars
    0.65
    IndentedString
    0.64
    addContainerGap
    0.62
     @"/
    0.62
    CppCodeGen
    0.61
     ProtoMessage
    0.60
     الحره
    0.59
    ISupport
    0.58
     kaarangay
    0.57
    Activations Density 10.079%

    No Known Activations