© 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. 5492
    Prev
    Next
    INDEX
    Explanations

    words that occur in formal statements or releases

    oai_token-act-pair · gemini-2.0-flash

    say statement

    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
    DockStyle
    -0.65
    findpost
    -0.62
    /**
    -0.59
    
    -0.58
     ujednoznacz
    -0.57
    AndEndTag
    -0.57
    tagHelperRunner
    -0.56
    csol
    -0.55
    verwijspagina
    -0.54
    goku
    -0.53
    POSITIVE LOGITS
    spesies
    0.59
     houſe
    0.53
    Espèce
    0.52
     FCS
    0.52
     pleaſure
    0.51
     Houſe
    0.50
     Theſe
    0.50
     poffe
    0.49
     faſt
    0.48
     tslint
    0.48
    Activations Density 6.618%

    No Known Activations