© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6507
    Prev
    Next
    INDEX
    Explanations

    acronyms especially in the context of scientific or engineering jargon

    oai_token-act-pair · gemini-2.0-flash

    say "k" 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
     vapa
    -0.55
     ää
    -0.44
     ilman
    -0.43
     hyö
    -0.42
     näytte
    -0.40
     suun
    -0.40
     tarko
    -0.40
     valmis
    -0.40
     osallist
    -0.39
     vaih
    -0.39
    POSITIVE LOGITS
     KEL
    1.02
     Kel
    1.00
     Kelley
    0.99
     Kard
    0.98
     KU
    0.98
    Kel
    0.98
     Kir
    0.98
     KF
    0.97
     Ket
    0.97
     KD
    0.96
    Activations Density 5.454%

    No Known Activations