© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8949
    Prev
    Next
    INDEX
    Explanations

    proper nouns and pronouns, sometimes along with nearby words

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    LookAnd
    -0.76
     myſelf
    -0.71
     Monfieur
    -0.68
    UnusedPrivate
    -0.64
     ***!
    -0.64
     Jefus
    -0.63
    parsedMessage
    -0.60
     كومونز
    -0.60
    TagHelper
    -0.59
     himſelf
    -0.59
    POSITIVE LOGITS
    itesi
    0.51
     g
    0.50
     kinerja
    0.48
    mazione
    0.48
     colher
    0.47
     most
    0.47
    ville
    0.47
    ITY
    0.47
     extérieures
    0.46
    ETERS
    0.46
    Activations Density 2.681%

    No Known Activations