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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14879
    Prev
    Next
    INDEX
    Explanations

    proper nouns and possessives

    oai_token-act-pair · gemini-2.0-flash

    book context

    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
    TestBed
    -0.46
     känd
    -0.43
     vinaigre
    -0.42
    tetur
    -0.41
    Specify
    -0.41
    mentaux
    -0.40
    Hire
    -0.39
    Suara
    -0.39
     evit
    -0.39
     adulti
    -0.39
    POSITIVE LOGITS
     himſelf
    0.81
    GEBURTSDATUM
    0.72
     EconPapers
    0.70
     myſelf
    0.70
    AddTagHelper
    0.69
    __':
    0.68
    __":
    0.65
     ſeveral
    0.64
    يكب
    0.64
    +#+#
    0.64
    Activations Density 3.220%

    No Known Activations