© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6170
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms, especially those which appear in all-caps

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns

    np_max-act-logits · gemini-2.0-flash

    capitalized name prefixes (3 letters)

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     itſelf
    -1.53
     Efq
    -1.49
     myſelf
    -1.48
    ſelf
    -1.44
    ſelves
    -1.40
     ―――――
    -1.38
     Monfieur
    -1.33
     Jefus
    -1.32
     Anſ
    -1.30
     doubtnut
    -1.30
    POSITIVE LOGITS
     
    0.86
     (
    0.79
    <eos>
    0.72
    ↵
    0.69
    ↵↵
    0.68
     -
    0.65
     N
    0.64
     C
    0.61
     B
    0.60
     et
    0.60
    Activations Density 1.704%

    No Known Activations