© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14336
    Prev
    Next
    INDEX
    Explanations

    verbs that describe physical actions that are negative

    oai_token-act-pair · gemini-2.0-flash

    say "him"

    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
     Wicidata
    -0.71
     disambiguazione
    -0.59
    they
    -0.59
    FunctionFlags
    -0.56
    SerializedSize
    -0.54
    Viitteet
    -0.54
    StoryboardSegue
    -0.54
    makeConstraints
    -0.54
     they
    -0.53
    ChildScrollView
    -0.53
    POSITIVE LOGITS
     him
    2.80
    him
    1.92
     Him
    1.91
    Him
    1.63
     HIM
    1.51
     ihn
    1.45
     honom
    1.39
     ihm
    1.30
    HIM
    1.27
     lui
    1.09
    Activations Density 2.986%

    No Known Activations