© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9907
    Prev
    Next
    INDEX
    Explanations

    code snippets and Q&A sections in technical documentation

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ↵
    -0.72
     her
    -0.57
     pos
    -0.56
     sent
    -0.51
     fall
    -0.50
     S
    -0.49
    ,
    -0.48
     é
    -0.48
     
    -0.48
     s
    -0.47
    POSITIVE LOGITS
     Theſe
    0.98
     itſelf
    0.86
     avoient
    0.84
     Efq
    0.82
     Monfieur
    0.80
     doubtnut
    0.79
     myſelf
    0.77
     CHAPITRE
    0.76
     Houſe
    0.75
     becauſe
    0.74
    Activations Density 1.893%

    No Known Activations