© 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. 6817
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to speculative fiction, or criticism of speculative fiction.

    oai_token-act-pair · gemini-2.0-flash

    past-tense actions

    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
    expandindo
    -0.70
     الاطلاع
    -0.57
     églises
    -0.56
     énergé
    -0.54
     médicaux
    -0.53
    Personendaten
    -0.52
     dieux
    -0.51
     timmar
    -0.51
     élector
    -0.49
     sauvages
    -0.48
    POSITIVE LOGITS
     committed
    0.65
     guided
    0.64
     faced
    0.63
     whoſe
    0.62
     terrified
    0.62
    tempted
    0.60
     trapped
    0.59
     forced
    0.59
     addicted
    0.59
     hampered
    0.58
    Activations Density 8.366%

    No Known Activations