© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15988
    Prev
    Next
    INDEX
    Explanations

    text related to giving something back

    oai_token-act-pair · gemini-2.0-flash

    returning money

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    IBar
    -0.62
    +#+
    -0.62
     onOptions
    -0.61
     насељу
    -0.61
     reactiv
    -0.60
    ้ำ
    -0.56
     resus
    -0.53
    ValueStyle
    -0.52
     reinstalled
    -0.52
    }{*}{}
    -0.49
    POSITIVE LOGITS
    Brainz
    0.64
    ThroughAttribute
    0.60
    ieteur
    0.60
    setVerticalGroup
    0.56
     springfox
    0.54
    براير
    0.51
    contentLoaded
    0.50
     kanssa
    0.50
    THX
    0.49
    :-)
    0.48
    Activations Density 0.937%

    No Known Activations