© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13539
    Prev
    Next
    INDEX
    Explanations

    words related to ability or options to do something

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ndi
    -0.46
     comun
    -0.44
      
    -0.41
    .'</
    -0.40
     saat
    -0.39
    CENTER
    -0.39
    vell
    -0.38
     suci
    -0.38
     approachable
    -0.38
    upsi
    -0.38
    POSITIVE LOGITS
     صوتيه
    1.02
    UserScript
    0.94
    AndEndTag
    0.88
    SourceChecksum
    0.87
    ChildScrollView
    0.84
    клопе
    0.84
    endphp
    0.81
     useAppContext
    0.79
    Datuak
    0.77
     समीक्षाओं
    0.77
    Activations Density 6.794%

    No Known Activations