© 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. 4779
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated things, including numbered lists, locations, railroad mentions, and academic references

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     RA
    -1.26
     RR
    -1.26
     RB
    -1.26
     RS
    -1.25
     RM
    -1.24
     RK
    -1.22
     Ro
    -1.22
     Ra
    -1.20
     RU
    -1.20
     RL
    -1.18
    POSITIVE LOGITS
    JsonInclude
    0.37
    IsContent
    0.36
    createCanvas
    0.31
    Inhalte
    0.29
    lemma
    0.28
    uncur
    0.28
     Amérique
    0.28
    zeige
    0.28
     Finlandia
    0.28
    хозяй
    0.28
    Activations Density 1.497%

    No Known Activations