© 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. 16262
    Prev
    Next
    INDEX
    Explanations

    words associated with bars and nightclubs

    oai_token-act-pair · gemini-2.0-flash

    bar

    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
     AssemblyCulture
    -0.64
    Enllaces
    -0.59
     فريبيس
    -0.59
     MainAxisSize
    -0.57
    elemField
    -0.53
     onCreateView
    -0.53
    ]--;
    -0.53
    writeFieldEnd
    -0.53
    ModelForm
    -0.52
    ussure
    -0.52
    POSITIVE LOGITS
     bar
    2.58
     bars
    2.30
    bar
    2.03
     Bar
    1.96
     Bars
    1.95
    bars
    1.91
    Bar
    1.87
    Bars
    1.82
    BAR
    1.73
     BAR
    1.63
    Activations Density 4.054%

    No Known Activations