© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10317
    Prev
    Next
    INDEX
    Explanations

    single character variables and parts of words that look like names or list-like data structures

    oai_token-act-pair · gemini-2.0-flash

    say "separators" Method used: 2 — tokens after are punctuation/separators

    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_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
    ↵↵
    -1.71
    ↵
    -1.64
    '
    -1.47
     
    -1.46
    <bos>
    -1.38
      
    -1.36
    ,
    -1.32
    1
    -1.29
     and
    -1.23
    .
    -1.23
    POSITIVE LOGITS
     myſelf
    2.44
     itſelf
    2.22
     Efq
    2.17
     purpoſe
    2.14
     iſt
    2.13
    ^(@)
    2.08
     ſeveral
    2.06
     Theſe
    2.02
     ―――――
    2.00
     greateſt
    2.00
    Activations Density 1.150%

    No Known Activations