© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2680
    Prev
    Next
    INDEX
    Explanations

    interrogative words and phrases related to opinions or suggestions

    oai_token-act-pair · gemini-2.0-flash

    questions and conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Efq
    -0.77
     ExecuteAsync
    -0.77
     Monfieur
    -0.74
    +#+#
    -0.72
    //
    -0.69
     snippetHide
    -0.66
    Xna
    -0.66
    ualaikum
    -0.65
    +:+
    -0.63
     pleaſure
    -0.62
    POSITIVE LOGITS
     so
    0.58
     denn
    0.52
     ConstraintSet
    0.50
    so
    0.47
    MathML
    0.47
     AUSSI
    0.47
    buc
    0.46
     Rol
    0.46
    </strong>
    0.45
     Manns
    0.45
    Activations Density 5.510%

    No Known Activations