© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9482
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to activate on a variety of seemingly unrelated tokens, without an obvious common pattern. It may be responding to a specific combination of tokens or other complex features not readily apparent

    oai_token-act-pair · gemini-2.0-flash

    And

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    دانشنامهٔ
    -0.88
     HasFactory
    -0.61
     Meksiku
    -0.59
     LiveData
    -0.57
    }{||
    -0.54
     AppModule
    -0.54
     harap
    -0.54
    JSONException
    -0.54
    gway
    -0.54
     BoxDecoration
    -0.52
    POSITIVE LOGITS
    <bos>
    0.79
    ConstraintMaker
    0.58
     <<<<<<<<<<<<<<
    0.54
    PyExc
    0.53
     saç
    0.49
    able
    0.48
     äta
    0.48
    PropertyChanging
    0.48
    ModelAdmin
    0.47
    ran
    0.47
    Activations Density 0.649%

    No Known Activations