© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12102
    Prev
    Next
    INDEX
    Explanations

    references to religious texts and biblical figures

    oai_token-act-pair · gemini-2.0-flash

    say ":"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.62
    ]--;
    -0.55
    ASING
    -0.54
    CPtr
    -0.54
    IRE
    -0.54
     StringTokenizer
    -0.53
    AndEndTag
    -0.52
    mäh
    -0.51
     nakalista
    -0.50
     समीक्षाएं
    -0.49
    POSITIVE LOGITS
    liferay
    0.52
     '\\;'
    0.52
    تقاوى
    0.47
    basicConfig
    0.47
    GoogleApiClient
    0.46
    quelize
    0.45
    лтамалар
    0.44
    Puck
    0.44
    yfik
    0.44
    Hyundai
    0.43
    Activations Density 1.236%

    No Known Activations