© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11619
    Prev
    Next
    INDEX
    Explanations

    place names, particularly locations in Antarctica

    oai_token-act-pair · gemini-2.0-flash

    words related to exploration

    np_token-act-pair-logits · gpt-4o-mini

    exploration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Välislingid
    -0.58
    Refinement
    -0.57
     समीक्षक
    -0.57
     kasarigan
    -0.56
     ppb
    -0.56
    RuleContext
    -0.55
    出版年
    -0.54
     ExecuteAsync
    -0.54
    ]--;
    -0.54
    IActionResult
    -0.53
    POSITIVE LOGITS
    exp
    0.71
    Exp
    0.69
     exploration
    0.67
     Exploration
    0.63
    Explore
    0.62
     explor
    0.60
     Explore
    0.60
    Expl
    0.60
    expl
    0.58
    Explor
    0.58
    Activations Density 0.984%

    No Known Activations