© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11767
    Prev
    Next
    INDEX
    Explanations

    the, some prepositions, and short statements within narratives.

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     the
    -0.70
     The
    -0.60
     as
    -0.57
     her
    -0.57
     B
    -0.55
     
    -0.54
     E
    -0.54
     to
    -0.54
     an
    -0.54
     a
    -0.52
    POSITIVE LOGITS
     Efq
    1.19
     Majefty
    1.16
     Anſ
    1.15
     Monfieur
    1.08
     myſelf
    1.06
    ſelf
    1.06
     Jefus
    1.05
     itſelf
    1.03
     themſelves
    1.01
     Reſ
    1.01
    Activations Density 4.617%

    No Known Activations