© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11271
    Prev
    Next
    INDEX
    Explanations

    instances of the word "is" or phrases containing the word "is" followed by an adjective or verb ending in "ing".

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    UnusedPrivate
    -0.90
     فريبيس
    -0.79
    RegressionTest
    -0.76
    expandindo
    -0.75
     autorytatywna
    -0.75
     linkovi
    -0.73
     <=",
    -0.73
     MainAxisSize
    -0.73
     @"/
    -0.73
    KURZBESCHREIBUNG
    -0.72
    POSITIVE LOGITS
     télécharge
    0.56
     nuages
    0.51
     réseaux
    0.47
     carottes
    0.47
    dojo
    0.46
     arrière
    0.46
    losigkeit
    0.45
     œufs
    0.45
     étoit
    0.45
    drucks
    0.44
    Activations Density 5.914%

    No Known Activations