© 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. 8590
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases and numbered citations, as well as some stray words nearby

    oai_token-act-pair · gemini-2.0-flash

    scientific 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_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
    así
    -0.55
    ISA
    -0.55
    ast
    -0.54
    AST
    -0.54
    stas
    -0.53
    ost
    -0.53
    
    -0.53
     grpc
    -0.52
     RIS
    -0.52
    isas
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.62
    rungsseite
    0.57
    spe
    0.51
    SBATCH
    0.49
     jsPsych
    0.49
     spe
    0.48
     Sep
    0.48
    selbe
    0.48
     vux
    0.46
    Sep
    0.46
    Activations Density 1.628%

    No Known Activations