© 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. 2483
    Prev
    Next
    INDEX
    Explanations

    email addresses or contact information

    oai_token-act-pair · gemini-2.0-flash

    email-related content

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

    email addresses

    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
     Wikimedijinoj
    -0.59
     quæ
    -0.59
     ainfi
    -0.57
     fidé
    -0.57
     étoient
    -0.57
     varandra
    -0.56
     houſe
    -0.56
     feroit
    -0.55
     démocr
    -0.54
     faſt
    -0.54
    POSITIVE LOGITS
    eapple
    0.59
    dinga
    0.59
     Acc
    0.58
    metz
    0.57
     AssemblyCulture
    0.56
    FXML
    0.56
     k
    0.56
     Neff
    0.56
     sweeps
    0.56
     j
    0.55
    Activations Density 2.875%

    No Known Activations