© 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. 15305
    Prev
    Next
    INDEX
    Explanations

    mentions of "token," instances of "away," and the phrase "System.Runtime."

    oai_token-act-pair · gemini-2.0-flash

    Software/Coding

    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
     myſelf
    -1.22
     auffi
    -1.16
     themſelves
    -1.10
     purpoſe
    -1.07
     uſed
    -1.05
     ſche
    -1.04
     anſ
    -1.03
     raiſ
    -1.03
     itſelf
    -1.02
     reaſon
    -1.02
    POSITIVE LOGITS
     R
    0.67
     E
    0.67
     P
    0.65
     I
    0.65
     D
    0.64
     De
    0.61
    /
    0.60
     Mor
    0.59
     “
    0.59
     at
    0.58
    Activations Density 0.684%

    No Known Activations