© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12929
    Prev
    Next
    INDEX
    Explanations

    present tense verbs such as 'is', 'are', or 'be'

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     a
    -0.59
     chi̍t
    -0.54
     is
    -0.52
    uegos
    -0.49
    DatabaseError
    -0.48
     ویکی‌پدی
    -0.46
     jest
    -0.46
     cú
    -0.44
    fromnode
    -0.44
    地上
    -0.44
    POSITIVE LOGITS
    CopyWith
    0.68
     виправивши
    0.63
    awtextra
    0.56
    SourceChecksum
    0.55
     CURIAM
    0.55
    airy
    0.54
    mergeFrom
    0.54
    campista
    0.53
     meaningless
    0.53
    localctx
    0.52
    Activations Density 1.862%

    No Known Activations