© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5562
    Prev
    Next
    INDEX
    Explanations

    a, an, not, or, names, and other seemingly random small words.

    oai_token-act-pair · gemini-2.0-flash

    Random mixed text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     مشين
    -0.77
    .",
    -0.73
    ReusableCell
    -0.73
     BitmapFactory
    -0.69
    '])->
    -0.69
    ModelAndView
    -0.69
     NavController
    -0.68
     Monfieur
    -0.68
    "]);
    -0.68
    ']);
    -0.68
    POSITIVE LOGITS
    ↵
    0.44
    gående
    0.43
     sélectionné
    0.41
     otomatis
    0.40
     satunya
    0.40
     like
    0.40
    ędz
    0.38
     como
    0.36
     flecha
    0.36
    幸
    0.36
    Activations Density 0.062%

    No Known Activations