© 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. 11629
    Prev
    Next
    INDEX
    Explanations

    negative contractions such as "don't" and similar constructions

    oai_token-act-pair · gemini-2.0-flash

    contractions ending in "n"

    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
     itſelf
    -1.23
    NUMX
    -1.20
     XNUMX
    -1.17
     ་་
    -1.16
     Reſ
    -1.15
     myſelf
    -1.12
     doubtnut
    -1.11
     raiſ
    -1.11
     Efq
    -1.11
     Anſ
    -1.10
    POSITIVE LOGITS
    ;
    0.56
     the
    0.52
     a
    0.49
     to
    0.45
     and
    0.43
     or
    0.36
    ly
    0.36
     in
    0.35
    ny
    0.34
    ness
    0.33
    Activations Density 0.485%

    No Known Activations