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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2347
    Prev
    Next
    INDEX
    Explanations

    instances of "to" preceded by a word

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "boot"

    np_token-act-pair-logits · gpt-4o-mini

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     >=",
    -0.59
    Халык
    -0.54
    ScopeManager
    -0.53
     forth
    -0.50
    KOK
    -0.47
    Pyx
    -0.45
     distanciation
    -0.44
    TestingModule
    -0.44
     Chippewa
    -0.43
     оригіналу
    -0.43
    POSITIVE LOGITS
     boot
    1.85
     Boot
    1.35
    boot
    1.29
    Boot
    1.20
     BOOT
    1.18
     boots
    0.96
     match
    0.95
    BOOT
    0.94
     booted
    0.90
     booting
    0.82
    Activations Density 1.319%

    No Known Activations