© 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. 8928
    Prev
    Next
    INDEX
    Explanations

    lines of code that start with a tab and an asterisk

    oai_token-act-pair · gemini-2.0-flash

    Code-related methods

    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
     tritium
    -0.62
     SIAM
    -0.59
     SMC
    -0.57
     uniqlo
    -0.57
     thermoc
    -0.57
     SCM
    -0.56
     Cholera
    -0.56
     *
    -0.56
     SRM
    -0.56
     MEG
    -0.56
    POSITIVE LOGITS
    ()][
    0.65
    kháu
    0.64
    ngdoc
    0.59
     Star
    0.59
     Jan
    0.58
    <!--[
    0.57
    WebVitals
    0.57
    an
    0.57
    modelBuilder
    0.57
     onAnimation
    0.57
    Activations Density 1.590%

    No Known Activations