© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8171
    Prev
    Next
    INDEX
    Explanations

    references to academic papers

    oai_token-act-pair · gemini-2.0-flash

    bracket "["

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ագրություններ
    -0.68
    醐
    -0.65
     /\.
    -0.61
    Дереккөздер
    -0.60
     ddelweddau
    -0.59
    Tikang
    -0.58
     noDo
    -0.57
    endpush
    -0.57
    elemField
    -0.54
     صوتيه
    -0.54
    POSITIVE LOGITS
    1
    0.47
    shown
    0.46
    compared
    0.45
    submitted
    0.44
    suggest
    0.43
    펴
    0.43
    4
    0.43
    suggested
    0.42
    reviewed
    0.42
     morire
    0.42
    Activations Density 12.078%

    No Known Activations