© 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. 7689
    Prev
    Next
    INDEX
    Explanations

    words relating to computing, geography, licensing of software, and organization names.

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    ļa
    -0.36
    pey
    -0.36
    Jereo
    -0.36
    Rüyada
    -0.35
    aj
    -0.35
    rith
    -0.34
    ResumeLayout
    -0.34
    )​
    -0.32
    ParseException
    -0.32
    */)
    -0.32
    POSITIVE LOGITS
     employs
    0.98
     Explains
    0.96
     inspires
    0.96
     encodes
    0.96
     engages
    0.96
     competes
    0.95
     uses
    0.93
    principalColumn
    0.93
     belongs
    0.93
     speaks
    0.93
    Activations Density 6.937%

    No Known Activations