© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5499
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and words describing emotions

    oai_token-act-pair · gemini-2.0-flash

    body and reactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     budaya
    -0.46
     chimiques
    -0.46
     medios
    -0.45
     suficientes
    -0.44
     proposons
    -0.44
     mantenga
    -0.43
     representación
    -0.43
    jahteraan
    -0.43
     trata
    -0.43
     tratta
    -0.42
    POSITIVE LOGITS
     itſelf
    0.90
    AsUp
    0.85
    ſelves
    0.85
     betweenstory
    0.84
    ſelf
    0.83
     Monfieur
    0.83
    Personensuche
    0.82
     Anſ
    0.82
     Efq
    0.81
     Majefty
    0.79
    Activations Density 1.687%

    No Known Activations