© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8124
    Prev
    Next
    INDEX
    Explanations

    evidence and logical connectors used to explain the rationale behind a statement

    oai_token-act-pair · gemini-2.0-flash

    therefore

    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
     itſelf
    -1.45
     himſelf
    -1.31
    AddTagHelper
    -1.29
     myſelf
    -1.26
     ſhe
    -1.23
     themſelves
    -1.10
     whoſe
    -1.06
     purpoſe
    -1.06
    ^(@)
    -1.06
    ſelf
    -1.06
    POSITIVE LOGITS
    .
    0.88
    ↵↵
    0.86
    ↵
    0.71
    ,
    0.70
     No
    0.66
    ;
    0.66
     Not
    0.66
     (
    0.65
    Maybe
    0.65
    '
    0.63
    Activations Density 3.081%

    No Known Activations