© 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. 7568
    Prev
    Next
    INDEX
    Explanations

    the prefix "under" and words it is attached to, as well as "over" when used as a prefix, and sometimes seems to activate to only the suffix of words that could have the prefix under

    oai_token-act-pair · gemini-2.0-flash

    under

    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
     فريبيس
    -0.81
     propOrder
    -0.77
    Under
    -0.70
    TypedDataSet
    -0.66
    under
    -0.66
     gynhyrchwyd
    -0.63
     invokingState
    -0.60
     kasarigan
    -0.59
    RegressionTest
    -0.59
    setVerticalGroup
    -0.57
    POSITIVE LOGITS
    teness
    0.52
    SourceChecksum
    0.52
    ธ์
    0.52
    unately
    0.51
    marginVertical
    0.50
    paddingVertical
    0.50
    ecord
    0.49
    litis
    0.49
    curity
    0.48
     nhiêu
    0.48
    Activations Density 6.587%

    No Known Activations