© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7569
    Prev
    Next
    INDEX
    Explanations

    itemized lists

    oai_token-act-pair · gemini-2.0-flash

    Code and lists

    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
     Efq
    -0.86
     fevere
    -0.79
     myſelf
    -0.75
     Monfieur
    -0.72
     uſed
    -0.71
     juſ
    -0.69
     raiſ
    -0.69
     itſelf
    -0.68
     Majefty
    -0.67
     pleaſure
    -0.66
    POSITIVE LOGITS
    isman
    0.57
     To
    0.56
    __((
    0.55
    styleType
    0.53
    -
    0.52
     star
    0.52
    <!--[
    0.51
     $
    0.50
    
    0.50
    ит
    0.49
    Activations Density 3.810%

    No Known Activations