© 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. 3154
    Prev
    Next
    INDEX
    Explanations

    noun phrases and sentences punctuated by periods and commas

    oai_token-act-pair · gemini-2.0-flash

    Legal/formal document extracts

    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
    DataAnnotations
    -0.45
    InSection
    -0.43
    AndEndTag
    -0.43
     ModelExpression
    -0.41
     المعيارى
    -0.39
    PageRoute
    -0.39
    twimg
    -0.39
    Portail
    -0.39
    teryx
    -0.39
    хьтан
    -0.38
    POSITIVE LOGITS
     Monfieur
    0.89
     Efq
    0.84
    كويكب
    0.76
    esterday
    0.73
     Jefus
    0.72
    plication
    0.72
     myſelf
    0.70
    ruct
    0.69
     himſelf
    0.68
     visualiser
    0.68
    Activations Density 12.901%

    No Known Activations