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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11062
    Prev
    Next
    INDEX
    Explanations

    CSS styling attributes

    oai_token-act-pair · gemini-2.0-flash

    radius

    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
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.66
    SourceChecksum
    -0.60
     GenerationType
    -0.60
     jsPsych
    -0.59
     hapa
    -0.55
     fitting
    -0.55
    Superview
    -0.55
     numberWith
    -0.53
     enfin
    -0.53
     angebra
    -0.51
    POSITIVE LOGITS
    openSession
    0.55
    COLN
    0.51
    accharides
    0.50
    uoja
    0.49
     forKey
    0.49
    ウンサー
    0.48
    Newswire
    0.48
    NamedQueries
    0.47
     tillgäng
    0.47
    AndEndTag
    0.46
    Activations Density 0.746%

    No Known Activations