© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6838
    Prev
    Next
    INDEX
    Explanations

    casual internet language

    oai_token-act-pair · gemini-2.0-flash

    I'm/don't

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Dont
    -1.51
     Dont
    -1.39
     dont
    -1.33
     youll
    -1.25
     doesnt
    -1.22
    dont
    -1.21
     isnt
    -1.16
     arent
    -1.15
     wasnt
    -1.15
     didnt
    -1.14
    POSITIVE LOGITS
    </b>
    0.48
    webElementXpaths
    0.47
     firm
    0.43
    (");
    0.42
     يكن
    0.42
    illeurs
    0.42
    iade
    0.42
     ReactDOM
    0.41
    тябрь
    0.41
    LikeLiked
    0.41
    Activations Density 3.550%

    No Known Activations