© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9671
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to playing, media consumption, and other forms of entertainment as well as things that are generally good.

    oai_token-act-pair · gemini-2.0-flash

    play

    np_max-act · gemini-2.0-flash

    play

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     played
    -1.28
    Playing
    -1.27
     play
    -1.26
     playing
    -1.25
     Playing
    -1.20
    Played
    -1.16
    playing
    -1.13
    played
    -1.11
     Played
    -1.09
     PLAY
    -1.05
    POSITIVE LOGITS
    脚注の使い方
    0.68
    ContentAlignment
    0.64
     publiques
    0.56
     proposées
    0.56
    transQ
    0.53
    JspWriter
    0.52
     فريبيس
    0.52
     Púb
    0.51
     fotogra
    0.51
    dellín
    0.51
    Activations Density 28.989%

    No Known Activations