© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2594
    Prev
    Next
    INDEX
    Explanations

    a variety of words ending in "s", or words that express scientific actions or math equations

    oai_token-act-pair · gemini-2.0-flash

    Technical parsing in texts

    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
     Malk
    -0.47
     got
    -0.46
     jog
    -0.45
    NOPQRST
    -0.44
     Jams
    -0.44
     bog
    -0.43
     odonto
    -0.43
     [*]
    -0.43
     BOG
    -0.43
     Caj
    -0.42
    POSITIVE LOGITS
    providedIn
    0.81
     ProtoMessage
    0.81
    UnusedPrivate
    0.73
     nahilalakip
    0.71
     propOrder
    0.70
    WithIOException
    0.68
     Roskov
    0.64
     Signalez
    0.60
    SharedDtor
    0.60
    IsContent
    0.59
    Activations Density 11.477%

    No Known Activations