© 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. 3669
    Prev
    Next
    INDEX
    Explanations

    references to God and his creations

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    存于互联网档案馆
    -0.79
    Personendaten
    -0.61
    expandindo
    -0.57
    出版年
    -0.56
     snippetHide
    -0.55
     متعلقه
    -0.54
     autorytatywna
    -0.52
     насељу
    -0.50
     joaat
    -0.50
     BoxFit
    -0.49
    POSITIVE LOGITS
    Msp
    0.52
    }());
    0.51
     kasarigan
    0.50
    getDoctrine
    0.48
     Defin
    0.48
    umenti
    0.47
     verk
    0.46
    estimm
    0.46
    ributors
    0.45
    isSet
    0.45
    Activations Density 2.512%

    No Known Activations