© 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. 11254
    Prev
    Next
    INDEX
    Explanations

    references to academic papers

    oai_token-act-pair · gemini-2.0-flash

    Dashes

    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
     Efq
    -1.12
    ſelf
    -1.08
     houſe
    -1.05
     myſelf
    -1.02
     itſelf
    -1.02
     Monfieur
    -1.00
     uſed
    -0.99
     Anſ
    -0.96
     Мексичка
    -0.96
     CreateTagHelper
    -0.96
    POSITIVE LOGITS
    -
    1.02
     -
    0.66
    –
    0.63
    —
    0.61
     –
    0.58
    _
    0.55
    --
    0.54
     
    0.52
     —
    0.48
    â
    0.48
    Activations Density 4.048%

    No Known Activations