© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15473
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and results

    oai_token-act-pair · gemini-2.0-flash

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Monfieur
    -0.96
     itſelf
    -0.88
     doubtnut
    -0.87
     ainfi
    -0.83
     fidé
    -0.83
     Anſ
    -0.77
     auroit
    -0.77
     plufieurs
    -0.77
     purpoſe
    -0.75
     Reſ
    -0.75
    POSITIVE LOGITS
     ag
    0.58
     infos
    0.56
     ver
    0.56
    VersionUID
    0.55
    pos
    0.54
     des
    0.54
     ressources
    0.54
    rungsseite
    0.53
     sind
    0.53
     qu
    0.52
    Activations Density 5.692%

    No Known Activations