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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3982
    Prev
    Next
    INDEX
    Explanations

    nouns associated with places and organizations, especially historical

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     Wicidata
    -0.76
    UnusedPrivate
    -0.66
     transférez
    -0.63
    IUrlHelper
    -0.58
    ScopeManager
    -0.58
     OFDb
    -0.58
     оригіналу
    -0.58
    CrossRef
    -0.57
     snippetHide
    -0.56
    NUMX
    -0.55
    POSITIVE LOGITS
     gostar
    0.52
     vrais
    0.50
     étrang
    0.50
     stället
    0.50
     attentes
    0.49
     religieuses
    0.48
     lige
    0.48
     chaude
    0.47
     fédé
    0.47
     nationaux
    0.47
    Activations Density 2.150%

    No Known Activations