© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11285
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    adaptiveStyles
    -0.62
    EndInit
    -0.60
    RuleContext
    -0.59
    requireNonNull
    -0.56
    ########.
    -0.55
    귀
    -0.54
    GEBURTSDATUM
    -0.53
    inheritdoc
    -0.53
    lawayo
    -0.53
     ecce
    -0.52
    POSITIVE LOGITS
    skog
    0.57
     Audiodateien
    0.54
    itchfield
    0.48
    ضايا
    0.47
    latego
    0.47
     CreateTagHelper
    0.46
     👆
    0.45
    Precis
    0.45
    GRANTED
    0.45
     consta
    0.44
    Activations Density 3.496%

    No Known Activations