© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 98
    Prev
    Next
    INDEX
    Explanations

    words related to countries, nationalities, and groups of people

    oai_token-act-pair · gemini-2.0-flash

    political texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Wikimedijinoj
    -0.63
    Rujukan
    -0.57
    ाहरण
    -0.56
     externi
    -0.55
     متعلقه
    -0.55
     Walkover
    -0.54
    sbericht
    -0.51
    turnstile
    -0.49
    CodedInputStream
    -0.48
     declar
    -0.46
    POSITIVE LOGITS
    ContentAsync
    0.71
    ModelSerializer
    0.56
     getIntent
    0.56
    <?
    0.55
    DllImport
    0.52
    ölker
    0.51
     banderas
    0.49
     combineReducers
    0.48
    didSet
    0.48
    FlatAppearance
    0.47
    Activations Density 2.726%

    No Known Activations