© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10391
    Prev
    Next
    INDEX
    Explanations

    prepositions used in certain phrases and contexts

    oai_token-act-pair · gemini-2.0-flash

    speaking engagements

    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
     speaking
    -2.70
     speaker
    -2.63
     speakers
    -2.45
     speak
    -2.44
     Speaking
    -2.31
     Speakers
    -2.28
    speaking
    -2.28
     spoke
    -2.22
    speaker
    -2.20
     Speaker
    -2.19
    POSITIVE LOGITS
    кипедия
    0.54
    ptest
    0.53
    webElementGuid
    0.52
     par
    0.51
     Paras
    0.49
    databinding
    0.48
     rubia
    0.48
    TypedDataSet
    0.47
    Par
    0.47
    igny
    0.45
    Activations Density 2.005%

    No Known Activations