© 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. 13197
    Prev
    Next
    INDEX
    Explanations

    words and phrases likely from Slovak and other Slavic languages

    oai_token-act-pair · gemini-2.0-flash

    account registration/verification text

    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
     malades
    -0.62
     clínicos
    -0.60
     precisione
    -0.60
     otomatig
    -0.60
     économies
    -0.58
     énergé
    -0.58
    everywhere
    -0.56
     beginnetje
    -0.56
     adaptarse
    -0.56
     personnelles
    -0.55
    POSITIVE LOGITS
     TestBed
    0.59
    Portale
    0.58
     POP
    0.52
    
    0.49
     flown
    0.48
    StructEnd
    0.48
    MathML
    0.47
     Pop
    0.47
     pop
    0.46
    Pop
    0.46
    Activations Density 0.445%

    No Known Activations