© 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. 10814
    Prev
    Next
    INDEX
    Explanations

    text discussing competitive racing events and winners

    oai_token-act-pair · gemini-2.0-flash

    cycling races

    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
    AndEndTag
    -0.98
    Geplaatst
    -0.97
    StoryboardSegue
    -0.95
    EDEFAULT
    -0.91
    httphttps
    -0.89
     Normdatei
    -0.88
    addContainerGap
    -0.87
     дописавши
    -0.85
     كومونز
    -0.82
    LookAnd
    -0.81
    POSITIVE LOGITS
     pró
    0.41
    ontin
    0.40
    INTEREST
    0.40
     contr
    0.39
     super
    0.39
    ്
    0.39
    edo
    0.38
    --]
    0.37
    gout
    0.37
    <bos>
    0.36
    Activations Density 1.083%

    No Known Activations