© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15150
    Prev
    Next
    INDEX
    Explanations

    sentences with personal pronouns and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    Negativity/disagreement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Panamoan
    -0.66
     kasarigan
    -0.64
     Oppen
    -0.61
     選手
    -0.57
     yoksa
    -0.54
     sanctuary
    -0.54
    VIAF
    -0.53
     Samara
    -0.53
    Попис
    -0.53
    ennies
    -0.52
    POSITIVE LOGITS
    setVerticalGroup
    0.63
    expandindo
    0.56
    NameInMap
    0.50
    ///</
    0.48
    पया
    0.48
    principalColumn
    0.47
    TabStop
    0.47
    Transkript
    0.43
    styleType
    0.43
    yeur
    0.41
    Activations Density 4.906%

    No Known Activations