© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6462
    Prev
    Next
    INDEX
    Explanations

    the word "ordinary" and words related to size, status or importance

    oai_token-act-pair · gemini-2.0-flash

    Ordinary or Largest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ing
    -0.71
    UTRAL
    -0.57
    isation
    -0.56
     VizieR
    -0.56
    ation
    -0.56
    ]='\
    -0.55
     quæ
    -0.54
    θεν
    -0.54
    oping
    -0.54
     @"";
    -0.54
    POSITIVE LOGITS
    <bos>
    1.05
     InputDecoration
    0.84
    contentLoaded
    0.82
    MigrationBuilder
    0.77
    ✨:
    0.73
    fillType
    0.73
    Autoritní
    0.72
    mybatisplus
    0.72
    yntaxException
    0.69
     unknownFields
    0.68
    Activations Density 0.480%

    No Known Activations