© 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. 4862
    Prev
    Next
    INDEX
    Explanations

    words related to enslavement or verbs ending in "ing", as well as some random other words.

    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
    Trait
    -0.35
     Restra
    -0.34
     potting
    -0.33
     Trait
    -0.31
     Practitioner
    -0.30
     whor
    -0.30
     Repar
    -0.29
     воз
    -0.29
    Morph
    -0.29
     Drill
    -0.29
    POSITIVE LOGITS
     تضيفلها
    1.06
    MigrationBuilder
    0.96
    bootstrapcdn
    0.95
    awtextra
    0.86
     ſeveral
    0.83
    GraphicsUnit
    0.81
    ftagPool
    0.81
     ་་
    0.79
     يتيمه
    0.78
    LookAnd
    0.78
    Activations Density 11.144%

    No Known Activations