© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15818
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and common verbs in both English and German

    oai_token-act-pair · gemini-2.0-flash

    forms of "have"

    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
     disambiguazione
    -0.77
    ArrowToggle
    -0.67
     is
    -0.67
     là
    -0.63
    protoimpl
    -0.57
     είναι
    -0.55
     Roskov
    -0.53
    是
    -0.52
    expandindo
    -0.52
     ialah
    -0.52
    POSITIVE LOGITS
     has
    1.95
    Has
    1.95
     Has
    1.86
    has
    1.84
     HAS
    1.45
    HAS
    1.39
     heeft
    1.14
     hath
    1.13
     hasn
    1.12
     έχει
    1.07
    Activations Density 10.714%

    No Known Activations