© 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. 4086
    Prev
    Next
    INDEX
    Explanations

    location names and geographic references

    oai_token-act-pair · gemini-2.0-flash

    plural nouns

    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
     Evaluations
    -0.73
     Jefus
    -0.73
     evaluations
    -0.73
     executions
    -0.68
    Comparisons
    -0.65
     Monfieur
    -0.65
     chofe
    -0.65
     houſe
    -0.64
     Majefty
    -0.64
     encounters
    -0.63
    POSITIVE LOGITS
     boards
    0.68
     clubs
    0.66
     дописавши
    0.63
     magazines
    0.63
     rivers
    0.63
     Boards
    0.63
     churches
    0.62
     lakes
    0.61
     Banks
    0.60
     buses
    0.60
    Activations Density 5.324%

    No Known Activations