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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16224
    Prev
    Next
    INDEX
    Explanations

    words related to prepositions and conjunctions

    oai_token-act-pair · gemini-2.0-flash

    for

    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
    ,
    -0.69
    ("")]
    -0.62
     and
    -0.59
     للمعارف
    -0.56
     or
    -0.54
    +#+#
    -0.54
    addGap
    -0.51
     ProtoMessage
    -0.51
    —
    -0.49
    RegressionTest
    -0.49
    POSITIVE LOGITS
     using
    0.78
    using
    0.75
     geologists
    0.75
     perfons
    0.72
    Using
    0.69
     skiers
    0.67
     photographers
    0.66
     himſelf
    0.66
     ſtate
    0.66
     dancers
    0.65
    Activations Density 11.863%

    No Known Activations