© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5794
    Prev
    Next
    INDEX
    Explanations

    words that look like proper nouns or titles

    oai_token-act-pair · 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
     is
    -0.58
     createState
    -0.54
     merupakan
    -0.53
     are
    -0.50
    は
    -0.50
     nargin
    -0.49
     έχει
    -0.49
     adalah
    -0.48
    Filmografie
    -0.48
     󰀄
    -0.48
    POSITIVE LOGITS
     so
    1.23
     when
    0.99
     prior
    0.97
     that
    0.96
     following
    0.95
     before
    0.94
     while
    0.93
     whom
    0.93
     after
    0.90
     whenever
    0.89
    Activations Density 14.556%

    No Known Activations