© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16356
    Prev
    Next
    INDEX
    Explanations

    the token "reg"

    oai_token-act-pair · gemini-2.0-flash

    reg

    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
    _
    -0.68
     the
    -0.59
     =
    -0.58
      
    -0.57
     <
    -0.56
     []:
    -0.56
    protoimpl
    -0.56
    <unused61>
    -0.55
     quie
    -0.53
    ...
    -0.52
    POSITIVE LOGITS
     Efq
    1.18
    ^(@)
    1.15
     photolibrary
    1.07
     doubtnut
    1.04
     myſelf
    0.99
    ſelf
    0.99
     itſelf
    0.99
     Forumite
    0.98
    ſelves
    0.98
     Majefty
    0.98
    Activations Density 1.474%

    No Known Activations