© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12475
    Prev
    Next
    INDEX
    Explanations

    hyphen-separated sequences of numbers and letters

    oai_token-act-pair · gemini-2.0-flash

    f

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    d
    -0.63
    p
    -0.59
    i
    -0.58
    r
    -0.56
     تضيفلها
    -0.54
    y
    -0.54
    l
    -0.53
    a
    -0.53
    //*[@
    -0.50
    י
    -0.49
    POSITIVE LOGITS
     يتيمه
    0.73
    〢
    0.59
    uities
    0.54
    انجليز
    0.54
    ypal
    0.54
    "])
    0.53
    ualitas
    0.53
    kémon
    0.51
     doInBackground
    0.51
    sisting
    0.50
    Activations Density 0.652%

    No Known Activations