© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6325
    Prev
    Next
    INDEX
    Explanations

    symbols and numbers in the context of machine learning

    oai_token-act-pair · gemini-2.0-flash

    Machine learning code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     vPvB
    -0.67
    +#+#
    -0.67
    writeField
    -0.66
    Спољашње
    -0.65
     محفوظة
    -0.63
    ConstraintMaker
    -0.60
     PhpStorm
    -0.60
    DOCTYPE
    -0.59
    anskje
    -0.58
    rungsseite
    -0.57
    POSITIVE LOGITS
     reconstructions
    0.50
     tensors
    0.50
     simulations
    0.49
     Bias
    0.49
     priors
    0.45
     buffs
    0.45
    Bias
    0.44
     tensor
    0.44
     embeddings
    0.44
     Embedding
    0.44
    Activations Density 29.506%

    No Known Activations