© 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. 13484
    Prev
    Next
    INDEX
    Explanations

    capitalized words related to governmental agencies or people involved in politics

    oai_token-act-pair · gemini-2.0-flash

    news/politics/law

    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
    ´
    -0.61
     ist
    -0.55
     «
    -0.53
     CanadaChoose
    -0.52
     adresses
    -0.52
     wich
    -0.51
     „
    -0.50
     adress
    -0.50
     infos
    -0.49
    الحياه
    -0.47
    POSITIVE LOGITS
     Monfieur
    1.39
     Theſe
    1.23
     Diſ
    1.19
     pleaſure
    1.10
     Anſ
    1.10
     ſever
    1.09
     Efq
    1.09
     Eſ
    1.08
     Perſ
    1.07
     Reſ
    1.07
    Activations Density 28.574%

    No Known Activations