© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15325
    Prev
    Next
    INDEX
    Explanations

    text related to augmented or virtual reality

    oai_token-act-pair · gemini-2.0-flash

    real reality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    SourceChecksum
    -0.62
     pinulongan
    -0.58
    RectangleBorder
    -0.55
     forgive
    -0.53
    IVEREF
    -0.50
     насељу
    -0.49
    ectady
    -0.48
     methodName
    -0.48
    انيف
    -0.48
    SequentialGroup
    -0.48
    POSITIVE LOGITS
     real
    1.76
    real
    1.71
     reality
    1.69
    Real
    1.59
     Real
    1.56
     REAL
    1.56
    REAL
    1.53
    reality
    1.45
    Reality
    1.37
     Reality
    1.35
    Activations Density 2.020%

    No Known Activations