© 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. 7662
    Prev
    Next
    INDEX
    Explanations

    technical documentation, specifically for a software tool

    oai_token-act-pair · gemini-2.0-flash

    Technical documentation

    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
     Advanced
    -0.64
     ADVANCED
    -0.62
    Advanced
    -0.61
    SourceChecksum
    -0.56
     feature
    -0.56
    Built
    -0.56
     Advance
    -0.56
    advanced
    -0.56
     advanced
    -0.54
     Built
    -0.53
    POSITIVE LOGITS
    endmodule
    0.63
     ویکی‌پدیای
    0.53
     Schicksal
    0.52
     otomatig
    0.51
     ويكيميديا
    0.51
     Medidas
    0.51
     CURIAM
    0.49
     macchina
    0.48
    izophren
    0.48
    criture
    0.47
    Activations Density 5.333%

    No Known Activations