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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13832
    Prev
    Next
    INDEX
    Explanations

    conjunctions used as the root word in common phrases.

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     noires
    -0.58
     inconnu
    -0.54
     plongée
    -0.53
     arché
    -0.53
     étoit
    -0.51
     vacanze
    -0.50
     religieuse
    -0.50
     russes
    -0.50
     scattata
    -0.49
     énergétique
    -0.49
    POSITIVE LOGITS
     unknownFields
    0.79
     EconPapers
    0.78
     kasarigan
    0.71
     שוליים
    0.71
     instruct
    0.70
     endorse
    0.69
     <",
    0.68
    Дереккөздер
    0.66
     compare
    0.65
     }}"></
    0.65
    Activations Density 6.775%

    No Known Activations