© 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. 12657
    Prev
    Next
    INDEX
    Explanations

    words describing parts of a building

    oai_token-act-pair · gemini-2.0-flash

    describing structures

    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
     eventdata
    -0.55
    esgue
    -0.48
    uxxxx
    -0.48
    TypeMap
    -0.48
     TextAppearance
    -0.47
     Scalars
    -0.46
    artiges
    -0.46
     propOrder
    -0.44
     Universiteit
    -0.44
    utnik
    -0.44
    POSITIVE LOGITS
    ########.
    0.91
    enumii
    0.72
    GEBURTSDATUM
    0.71
     stores
    0.68
     store
    0.66
    store
    0.63
    rungsseite
    0.63
     STORE
    0.62
     houſe
    0.62
    +#+
    0.61
    Activations Density 9.615%

    No Known Activations