Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14252
    Prev
    Next
    INDEX
    Explanations

    sentences that contain speculation about the future

    oai_token-act-pair · gemini-2.0-flash

    formal, academic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     lèvres
    -0.45
     незавершена
    -0.41
     deberes
    -0.41
     leçons
    -0.41
     houver
    -0.40
     trekken
    -0.40
     ongles
    -0.39
     entendido
    -0.38
     prochaines
    -0.38
     laikā
    -0.38
    POSITIVE LOGITS
     juſ
    0.70
     ſou
    0.69
     ſche
    0.69
     Perſ
    0.68
     Jefus
    0.67
     ſta
    0.67
     ſch
    0.66
     ſol
    0.65
     Reſ
    0.64
     Diſ
    0.64
    Activations Density 6.572%

    No Known Activations