© 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. 4908
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags

    oai_token-act-pair · gemini-2.0-flash

    say "s" words

    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
     SN
    -0.97
     SZ
    -0.91
     SV
    -0.90
     SB
    -0.90
     SCO
    -0.89
     SL
    -0.89
     SM
    -0.88
     SJ
    -0.88
     Sb
    -0.87
     SF
    -0.87
    POSITIVE LOGITS
     <=",
    0.57
    ship
    0.52
    systems
    0.48
    space
    0.48
    shop
    0.47
    findpost
    0.47
    s
    0.46
    song
    0.46
    some
    0.45
    school
    0.44
    Activations Density 4.785%

    No Known Activations