© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6751
    Prev
    Next
    INDEX
    Explanations

    the word "stop" and words and phrases similar to it, or describing it in some way.

    oai_token-act-pair · gemini-2.0-flash

    stop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    +#+#
    -0.83
    RenderAtEndOf
    -0.74
     Stopping
    -0.74
     Stops
    -0.71
     stopping
    -0.68
    Stopping
    -0.66
     publiques
    -0.64
    stopping
    -0.64
     stops
    -0.64
     stoppage
    -0.63
    POSITIVE LOGITS
     the
    0.55
    Билгалдахарш
    0.54
     autorytatywna
    0.53
    UnitTesting
    0.53
     in
    0.49
    endenza
    0.46
     on
    0.44
     intptr
    0.44
     propOrder
    0.44
     and
    0.44
    Activations Density 11.707%

    No Known Activations