© 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. 419
    Prev
    Next
    INDEX
    Explanations

    words and prefixes like "inter-", "intra-", "bio-", "medu-", "pul-" and "osteo-" that have to do with relationships or within some body.

    oai_token-act-pair · gemini-2.0-flash

    inter/intra

    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
    Ex
    -0.58
    Inter
    -0.57
    En
    -0.56
    Form
    -0.56
    State
    -0.56
    Di
    -0.55
    Al
    -0.55
    Health
    -0.55
    Cons
    -0.54
    Un
    -0.54
    POSITIVE LOGITS
    Còn
    0.58
    ORING
    0.51
    ETIES
    0.51
    FTFY
    0.50
    ERÍA
    0.49
    jungle
    0.48
     zwey
    0.47
    dough
    0.47
    ISHMENT
    0.47
     ครับ
    0.47
    Activations Density 4.048%

    No Known Activations