© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2940
    Prev
    Next
    INDEX
    Explanations

    words that begin with "res", "pos", "uns", "us", and "es"

    oai_token-act-pair · gemini-2.0-flash

    nonsensical text and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    OnError
    -0.44
     derog
    -0.43
    ocer
    -0.42
    Author
    -0.41
    her
    -0.41
    مصادر
    -0.40
     yle
    -0.40
    ars
    -0.40
    是她
    -0.39
    getOutputStream
    -0.39
    POSITIVE LOGITS
     ModelExpression
    0.91
    Демографія
    0.82
    adaptiveStyles
    0.79
    WithIOException
    0.77
     utafitiHapana
    0.71
    ThroughAttribute
    0.71
    httphttps
    0.70
    "):
    0.69
     invokingState
    0.68
     المعيارى
    0.68
    Activations Density 0.435%

    No Known Activations