© 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. 471
    Prev
    Next
    INDEX
    Explanations

    first-person plural present tense verbs, and other keywords suggesting ongoing action and events.

    oai_token-act-pair · gemini-2.0-flash

    business/financial performance updates

    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
    LookAnd
    -0.99
    WriteTagHelper
    -0.90
    ConstraintMaker
    -0.82
    rungsseite
    -0.79
    AccessorTable
    -0.76
     typelib
    -0.75
    SharedCtor
    -0.73
    webElementXpaths
    -0.72
    SourceChecksum
    -0.71
    tonsoft
    -0.69
    POSITIVE LOGITS
    mistry
    0.51
    AsUp
    0.43
     BytesLike
    0.42
    礙
    0.40
    èvement
    0.40
    ردن
    0.40
     Stampa
    0.39
    נצ
    0.39
    λευτα
    0.39
    ungk
    0.39
    Activations Density 4.422%

    No Known Activations