© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10474
    Prev
    Next
    INDEX
    Explanations

    the word "once", and sometimes activates when it appears near the words "when", "as", and "whenever"

    oai_token-act-pair · gemini-2.0-flash

    once

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     once
    -2.25
    once
    -2.23
     Once
    -2.09
    Once
    -2.08
     ONCE
    -1.90
    ONCE
    -1.77
     einmal
    -1.27
    一旦
    -1.09
    一度
    -1.08
     sekali
    -1.00
    POSITIVE LOGITS
     Roskov
    0.64
     المعيارى
    0.61
    UnknownFields
    0.60
     BoxDecoration
    0.59
    rungsseite
    0.59
    findpost
    0.58
    EDEFAULT
    0.57
     AutoMapper
    0.56
    RefNanny
    0.56
    </thead>
    0.54
    Activations Density 2.529%

    No Known Activations