© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15397
    Prev
    Next
    INDEX
    Explanations

    a high diversity of joining words, prepositions, and words that indicate location or dependence.

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     TERMS
    -0.51
    BindingResult
    -0.49
     Terms
    -0.49
    
    -0.47
    новниш
    -0.47
    TEMPO
    -0.47
    شهاد
    -0.46
     regards
    -0.46
    Terms
    -0.46
     Requis
    -0.46
    POSITIVE LOGITS
    ImageIO
    0.60
     kasarigan
    0.58
    providedIn
    0.55
     للاسماء
    0.54
    AndView
    0.54
    Geplaatst
    0.53
    </tfoot>
    0.52
     defaultstate
    0.52
    InitVars
    0.52
     tartalomajánló
    0.50
    Activations Density 4.878%

    No Known Activations