© 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. 11329
    Prev
    Next
    INDEX
    Explanations

    adverbs that intensify a statement or opinion

    oai_token-act-pair · gemini-2.0-flash

    positive reviews

    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
     betweenstory
    -0.55
    have
    -0.54
    دانشنامهٔ
    -0.52
     have
    -0.50
     Have
    -0.47
     curves
    -0.47
    ctibles
    -0.47
    amme
    -0.46
    ímos
    -0.46
     figures
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.66
     were
    0.59
     disponibilités
    0.57
    Were
    0.56
     Were
    0.54
    AddTagHelper
    0.52
    SharedDtor
    0.52
    InstanceState
    0.50
     Signalez
    0.50
    //});
    0.50
    Activations Density 14.099%

    No Known Activations