© 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. 6366
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal or formal arguments alongside names of people or corporations.

    oai_token-act-pair · gemini-2.0-flash

    Single letters

    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
     photolibrary
    -0.68
    ^(@)
    -0.59
    })*/
    -0.57
    tvguidetime
    -0.57
    
    -0.56
    Referencies
    -0.54
    sidemargin
    -0.53
    ükemmel
    -0.52
     stiefel
    -0.51
    !")
    -0.51
    POSITIVE LOGITS
    L
    1.00
    Z
    0.95
    M
    0.92
    D
    0.91
    W
    0.91
    C
    0.90
    H
    0.90
    G
    0.90
    F
    0.90
    LS
    0.90
    Activations Density 28.090%

    No Known Activations