© 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. 12756
    Prev
    Next
    INDEX
    Explanations

    the prefix "sub-"

    oai_token-act-pair · gemini-2.0-flash

    sub

    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
     للاسماء
    -0.87
    MemoryWarning
    -0.84
    UserScript
    -0.81
    EndGlobalSection
    -0.80
    
    -0.75
    \{\\
    -0.74
    ValueStyle
    -0.74
    ::_('
    -0.73
    SequentialGroup
    -0.71
    }}^{(
    -0.71
    POSITIVE LOGITS
    jst
    0.41
    versi
    0.38
    ToLeft
    0.36
     povol
    0.36
     ngoài
    0.36
     ridurre
    0.36
    ğe
    0.36
     etme
    0.36
     minimum
    0.35
    vers
    0.34
    Activations Density 0.319%

    No Known Activations