© 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. 6151
    Prev
    Next
    INDEX
    Explanations

    pronouns and words related to history and mathematics

    oai_token-act-pair · gemini-2.0-flash

    reduction

    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
    Portály
    -0.70
    IsMutable
    -0.58
    UnsafeEnabled
    -0.57
     CreateTagHelper
    -0.55
     Administrativna
    -0.54
     autorytatywna
    -0.53
    GZIP
    -0.52
    Gweler
    -0.52
    InjectAttribute
    -0.50
    ENOMEM
    -0.50
    POSITIVE LOGITS
     reduced
    0.56
    Reduced
    0.56
    reduced
    0.56
     []:
    0.54
     Reduced
    0.52
     reduction
    0.52
     réduction
    0.51
     reducing
    0.51
    reduce
    0.51
     reduces
    0.50
    Activations Density 11.748%

    No Known Activations