© 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. 11317
    Prev
    Next
    INDEX
    Explanations

    contractions and auxiliaries like 'is', 've', 's', 'it's', 'just' and some related words

    oai_token-act-pair · gemini-2.0-flash

    s

    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
    ever
    -0.66
    ."]
    -0.65
     '}
    -0.58
     defaultstate
    -0.57
     ویکی‌پدی
    -0.57
    '}>
    -0.57
     TAKEN
    -0.57
    rather
    -0.56
    '}
    -0.56
     ever
    -0.56
    POSITIVE LOGITS
    planner
    0.52
     Grecs
    0.51
     skolen
    0.51
    ztály
    0.51
     vícti
    0.50
    constraints
    0.49
    icleta
    0.49
     proofs
    0.49
     elasticity
    0.48
    новништво
    0.48
    Activations Density 3.877%

    No Known Activations