© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10763
    Prev
    Next
    INDEX
    Explanations

    text in all caps, associated with legal, technical or formal documents.

    oai_token-act-pair · gemini-2.0-flash

    Legal and business texts

    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
     ad
    -0.78
    ad
    -0.69
     transfieras
    -0.63
     tartalomajánló
    -0.60
    Ad
    -0.59
     IS
    -0.58
     OFDb
    -0.57
    dział
    -0.56
     '{@
    -0.54
     SHALL
    -0.53
    POSITIVE LOGITS
     UN
    1.66
    UN
    1.39
     UNS
    1.05
     UNA
    0.88
     UNE
    0.86
    UNC
    0.83
     EN
    0.83
     AN
    0.81
     WHO
    0.79
     UNF
    0.77
    Activations Density 3.247%

    No Known Activations