© 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. 11153
    Prev
    Next
    INDEX
    Explanations

    mentions of seeing, reading, enjoying, discovering, or having a feeling

    oai_token-act-pair · gemini-2.0-flash

    see

    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
    <bos>
    -0.89
    SourceChecksum
    -0.84
    astéroïdes
    -0.69
    SequentialGroup
    -0.67
     ligiloj
    -0.66
    #+#
    -0.60
    __':
    -0.58
    elemField
    -0.56
     الرياضيه
    -0.53
     مواليد
    -0.51
    POSITIVE LOGITS
    dafx
    0.61
    Hauptartikel
    0.52
    हां
    0.51
    GOTREF
    0.51
    adors
    0.50
    HtmlAttribute
    0.50
     beginnetje
    0.50
     ftate
    0.49
    Yn
    0.49
     plant
    0.48
    Activations Density 6.570%

    No Known Activations