© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10215
    Prev
    Next
    INDEX
    Explanations

    instances of the word "durable" and hardware

    oai_token-act-pair · gemini-2.0-flash

    durable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ^(@)
    -1.44
     myſelf
    -1.25
     étoit
    -1.20
    setVerticalGroup
    -1.15
     pleaſure
    -1.14
    يميديا
    -1.14
     Monfieur
    -1.14
     étoient
    -1.13
     Jefus
    -1.13
     Forumite
    -1.12
    POSITIVE LOGITS
    <eos>
    1.05
    .
    1.00
    1
    0.84
    9
    0.81
    3
    0.78
    2
    0.77
    V
    0.76
    ,
    0.76
    8
    0.76
    5
    0.75
    Activations Density 0.371%

    No Known Activations