© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13569
    Prev
    Next
    INDEX
    Explanations

    phrases like "went on to say", "go on to play," "drugs to treat", or other uses of "on to" followed by a verb.

    oai_token-act-pair · gemini-2.0-flash

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    CloseOperation
    -0.48
    pecific
    -0.48
    hObject
    -0.47
    specific
    -0.47
     Audiodateien
    -0.46
     specific
    -0.46
    sproz
    -0.46
     prosegu
    -0.45
    進
    -0.44
    cloudfront
    -0.43
    POSITIVE LOGITS
    AccessorTable
    0.65
    AndEndTag
    0.61
    loem
    0.60
    RegistryLite
    0.60
    \{\\
    0.60
     onOptions
    0.56
     HasFactory
    0.54
    ParseTree
    0.54
    EndContext
    0.53
    wts
    0.53
    Activations Density 10.580%

    No Known Activations