© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 495
    Prev
    Next
    INDEX
    Explanations

    words relating to teaching children phonics in school

    oai_token-act-pair · gemini-2.0-flash

    Educational material and code examples

    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
     informée
    -0.63
     protoimpl
    -0.59
     Freeport
    -0.54
     محفوظة
    -0.54
    HomeAsUpEnabled
    -0.50
    SerializedSize
    -0.49
    цездатний
    -0.48
    bootstrapcdn
    -0.46
     Ud
    -0.46
     gobernador
    -0.46
    POSITIVE LOGITS
    DeleteBehavior
    0.66
     unknownFields
    0.57
     ReactDOM
    0.54
     doInBackground
    0.53
    WebServlet
    0.51
     filo
    0.51
    OGND
    0.50
    strtotime
    0.49
    ;->
    0.49
    stateProvider
    0.49
    Activations Density 3.060%

    No Known Activations