© 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. 5219
    Prev
    Next
    INDEX
    Explanations

    a variety of things: some dialogue and some violent actions, along with an enthusiasm for some graphic sexual acts.

    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
     يتيمه
    -0.66
    formik
    -0.51
    thodoxy
    -0.50
    endenza
    -0.49
    hastly
    -0.48
    anyahu
    -0.48
    AnimationsModule
    -0.48
    abling
    -0.48
     uintptr
    -0.47
     Power
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.75
    RefNanny
    0.61
     تضيفلها
    0.57
    CopyWith
    0.56
    TabStop
    0.56
     AttributeSet
    0.55
    postsleuth
    0.49
     camicia
    0.49
    reactstrap
    0.49
     jadx
    0.49
    Activations Density 1.621%

    No Known Activations