© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2038
    Prev
    Next
    INDEX
    Explanations

    questions asking for an explanation of the difference between two things

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     difference
    -2.67
     Difference
    -2.58
    diff
    -2.56
     diff
    -2.53
     differences
    -2.53
    Diff
    -2.48
     Differences
    -2.47
    difference
    -2.45
    differ
    -2.44
    Difference
    -2.41
    POSITIVE LOGITS
     externi
    0.64
    bolista
    0.62
     дописавши
    0.59
    yorsunuz
    0.57
     preghi
    0.52
    ließlich
    0.47
    rsiniz
    0.46
     مشين
    0.45
    istoitu
    0.45
    odan
    0.45
    Activations Density 6.215%

    No Known Activations