© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11347
    Prev
    Next
    INDEX
    Explanations

    common words such as "the", "of", and "in", especially when appearing together

    oai_token-act-pair · gemini-2.0-flash

    gaining confidence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    expandindo
    -0.85
     незавершена
    -0.73
     समीक्षाओं
    -0.68
    Personensuche
    -0.67
     nahilalakip
    -0.64
    __':
    -0.62
    PropertyChanging
    -0.62
    __":
    -0.60
    NewUrlParser
    -0.60
    XmlAccessorType
    -0.59
    POSITIVE LOGITS
     ThemeData
    0.55
    Források
    0.54
    ñal
    0.54
     aikana
    0.51
     palvel
    0.50
     valmis
    0.49
     alugar
    0.48
    astéro
    0.47
     paſſ
    0.46
     myſelf
    0.46
    Activations Density 2.625%

    No Known Activations