© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9742
    Prev
    Next
    INDEX
    Explanations

    various function words or prepositions/conjunctions that commonly connect other parts of speech together.

    oai_token-act-pair · gemini-2.0-flash

    Functions, actions, processes

    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
    ρκ
    -0.49
     drops
    -0.48
    )++;
    -0.48
    ,:),
    -0.47
    dro
    -0.47
     grow
    -0.47
    grow
    -0.46
     sto
    -0.46
     diagnosing
    -0.44
    ]();
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.71
    RegistryLite
    0.69
     defaultstate
    0.68
    ContentAlignment
    0.65
    RTLD
    0.65
     makeStyles
    0.64
    Jereo
    0.62
     незавершена
    0.62
    JoinTable
    0.61
    yntaxException
    0.59
    Activations Density 5.108%

    No Known Activations