© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13876
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers within text

    oai_token-act-pair · gemini-2.0-flash

    numerical data and percentages

    np_token-act-pair-logits · gpt-4o-mini

    say single digit number

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ChildScrollView
    -0.88
     propOrder
    -0.87
    WriteAttribute
    -0.81
    ValueStyle
    -0.78
    CodedInputStream
    -0.75
    tvguidetime
    -0.73
     صوتيه
    -0.73
    LayoutStyle
    -0.70
     disambiguazione
    -0.70
     purpoſe
    -0.70
    POSITIVE LOGITS
     Lew
    0.47
     close
    0.45
     düzen
    0.43
     some
    0.42
     dział
    0.40
     bereit
    0.40
    parseFrom
    0.38
     mivel
    0.37
     
    0.37
    5
    0.37
    Activations Density 1.348%

    No Known Activations