© 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. 6162
    Prev
    Next
    INDEX
    Explanations

    somewhat random words and phrases

    oai_token-act-pair · 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
     disrupting
    -1.06
     robbing
    -0.98
     interfering
    -0.98
     disruption
    -0.97
     destroying
    -0.96
     Blocking
    -0.96
     blocking
    -0.94
     interrupting
    -0.93
     tearing
    -0.93
     interference
    -0.93
    POSITIVE LOGITS
    anga
    0.41
    extré
    0.38
     coppia
    0.38
     oprot
    0.36
     kon
    0.36
    ínguez
    0.35
     stationary
    0.35
    Cuándo
    0.35
    付
    0.34
     d
    0.34
    Activations Density 1.412%

    No Known Activations