© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6435
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially Javascript or C#, containing symbols like '=', '(', ')', '{', or '!'

    oai_token-act-pair · gemini-2.0-flash

    programming syntax

    np_token-act-pair-logits · gpt-4o-mini

    = or (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    yes
    -0.59
     yes
    -0.53
    laß
    -0.49
     OK
    -0.48
    vaného
    -0.47
     điểm
    -0.47
    Diweddarwch
    -0.47
    Set
    -0.47
    aughey
    -0.46
    okay
    -0.46
    POSITIVE LOGITS
    NUMX
    0.72
     pleaſure
    0.69
    ſelf
    0.69
     faſt
    0.68
     ſtate
    0.66
     houſe
    0.65
     itſelf
    0.64
     Beſ
    0.61
     Monfieur
    0.60
    TemporalType
    0.60
    Activations Density 2.905%

    No Known Activations