© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9688
    Prev
    Next
    INDEX
    Explanations

    negative statements about government and politics from a historical context

    oai_token-act-pair · gemini-2.0-flash

    legal and historical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    hek
    -0.61
     capuche
    -0.57
     Houſe
    -0.52
    bán
    -0.52
    AlertDialog
    -0.51
     Berech
    -0.51
     olev
    -0.50
    ština
    -0.50
     Estre
    -0.50
    mediately
    -0.49
    POSITIVE LOGITS
     propOrder
    0.59
    出版年
    0.59
    RectangleBorder
    0.56
     Normdatei
    0.55
     protoimpl
    0.55
    IntoConstraints
    0.54
    исленность
    0.53
    VolleyError
    0.53
    ierzch
    0.52
    MLLoader
    0.52
    Activations Density 1.580%

    No Known Activations