© 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. 9844
    Prev
    Next
    INDEX
    Explanations

    scientific or technical words relating to measurement and sensing at a nano scale

    oai_token-act-pair · gemini-2.0-flash

    based

    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
    awtextra
    -0.69
     artikkeli
    -0.67
     küpe
    -0.64
    Hentet
    -0.63
     scattata
    -0.63
    ="{{$
    -0.61
    posedge
    -0.60
     médec
    -0.60
    AnimationsModule
    -0.60
    ="<?=$
    -0.59
    POSITIVE LOGITS
    ing
    0.41
    gameserver
    0.40
     us
    0.37
     Hift
    0.37
     ret
    0.37
     are
    0.36
     متعلقه
    0.35
    toMatch
    0.35
     meet
    0.35
    hive
    0.35
    Activations Density 7.983%

    No Known Activations