© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10011
    Prev
    Next
    INDEX
    Explanations

    religious language and supplication

    oai_token-act-pair · 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
    RegistryLite
    -0.79
     Normdatei
    -0.74
     Roskov
    -0.73
    uxxxx
    -0.71
    SourceChecksum
    -0.69
    PhysRev
    -0.65
    thâu
    -0.65
    ItemBackground
    -0.65
     متعلقه
    -0.65
     '\\;'
    -0.65
    POSITIVE LOGITS
     kuasa
    0.44
    __]
    0.44
     lái
    0.43
     Schles
    0.42
     öffnet
    0.42
    dison
    0.42
    ngthen
    0.41
    setImageResource
    0.40
    艋
    0.39
    Cyfarwyddwr
    0.39
    Activations Density 0.662%

    No Known Activations