© 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. 13001
    Prev
    Next
    INDEX
    Explanations

    the token sequence "Pop...ulated places"

    oai_token-act-pair · gemini-2.0-flash

    pop

    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
     pop
    -3.22
     Pop
    -3.02
    Pop
    -2.94
    pop
    -2.89
     POP
    -2.77
    POP
    -2.75
     pops
    -2.39
     popped
    -2.25
     popping
    -2.14
     popup
    -2.13
    POSITIVE LOGITS
    diyesi
    0.65
    MLLoader
    0.63
     linkovi
    0.62
    AndEndTag
    0.59
    ClientSize
    0.56
     مرئيه
    0.56
     مشين
    0.56
    ########.
    0.53
    شهاد
    0.53
    iastes
    0.52
    Activations Density 2.443%

    No Known Activations