© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4518
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to continued action, maintenance, and dependence.

    oai_token-act-pair · gemini-2.0-flash

    continue/survive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    Архівовано
    -0.71
    Pautan
    -0.65
    ContentAlignment
    -0.63
    mybatisplus
    -0.63
    SceneManagement
    -0.62
     تضيفلها
    -0.61
    Diweddarwch
    -0.60
    gypti
    -0.60
     مشين
    -0.59
    󠁢
    -0.59
    POSITIVE LOGITS
     continuance
    1.40
     continuation
    1.30
     continued
    1.29
     continue
    1.23
     continuing
    1.20
     survival
    1.20
    continue
    1.16
     continues
    1.10
     survive
    1.09
     Survival
    1.05
    Activations Density 2.027%

    No Known Activations