© 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. 7634
    Prev
    Next
    INDEX
    Explanations

    a mixed bag of words related to a variety of things from food reviews to political discussion to reflection.

    oai_token-act-pair · 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
     us
    -3.25
     Us
    -1.86
    us
    -1.73
    Us
    -1.66
     нас
    -1.47
     me
    -1.40
     нами
    -1.23
     нам
    -1.21
     nosotros
    -1.19
     nás
    -1.14
    POSITIVE LOGITS
     ::=
    0.47
    Elenco
    0.47
    rimid
    0.47
    rimidine
    0.46
    ModelAdmin
    0.45
     roze
    0.44
    VELAND
    0.44
    
    0.44
    ungle
    0.44
    crites
    0.43
    Activations Density 7.727%

    No Known Activations