© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4848
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and numbers

    oai_token-act-pair · gemini-2.0-flash

    -

    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
     kasarigan
    -0.88
    MessageOf
    -0.84
    ngdoc
    -0.71
    Geplaatst
    -0.69
    tonsoft
    -0.63
    EndProject
    -0.62
    by
    -0.61
     otomatig
    -0.59
     ModelExpression
    -0.57
    neath
    -0.57
    POSITIVE LOGITS
    y
    1.06
    ye
    0.78
    yal
    0.72
    yle
    0.72
    yon
    0.71
    yl
    0.69
    yo
    0.69
    yi
    0.65
    yc
    0.65
    yse
    0.65
    Activations Density 12.635%

    No Known Activations