© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14651
    Prev
    Next
    INDEX
    Explanations

    descriptive language of scenes with people feeling tension

    oai_token-act-pair · gemini-2.0-flash

    looking/staring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Espèce
    -0.55
    ifan
    -0.54
     '\\;'
    -0.53
     ویکی‌پدی
    -0.52
     rapides
    -0.52
     nonUne
    -0.52
    ंदीखरीदारी
    -0.49
     kokona
    -0.49
     pauvres
    -0.47
     gynhyrchwyd
    -0.46
    POSITIVE LOGITS
    enumi
    0.63
     GoogleFonts
    0.57
     Wide
    0.57
     ap
    0.56
    neutron
    0.56
    Fixes
    0.54
    Weiterlesen
    0.54
     open
    0.53
    eaway
    0.51
    สบ
    0.51
    Activations Density 1.098%

    No Known Activations