© 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. 5889
    Prev
    Next
    INDEX
    Explanations

    mentions of figures, tables, results, subjects, photons, phases and tables in scientific writing.

    oai_token-act-pair · gemini-2.0-flash

    say "illustration/summary words"

    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
     defaultstate
    -0.66
     Showing
    -0.60
    Showing
    -0.60
    ']),
    -0.56
     showing
    -0.55
    \}\\
    -0.54
    )$_
    -0.52
    )*/
    -0.52
    rawDesc
    -0.52
    ])))
    -0.51
    POSITIVE LOGITS
     tolerance
    0.54
    armament
    0.53
    rungsseite
    0.52
     absorption
    0.52
     createState
    0.51
     aberration
    0.50
     народов
    0.50
     periodicity
    0.50
     reflectivity
    0.50
     privées
    0.50
    Activations Density 13.344%

    No Known Activations