© 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. 15899
    Prev
    Next
    INDEX
    Explanations

    words related to travel, motherhood, or personal experiences

    oai_token-act-pair · gemini-2.0-flash

    abstract nouns

    np_max-act-logits · gemini-2.0-flash

    say "verbs of change"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Come
    -0.82
     Come
    -0.80
    come
    -0.73
     Fall
    -0.70
    RegressionTest
    -0.70
    COME
    -0.69
     للمعارف
    -0.69
    Fall
    -0.69
    FALL
    -0.66
     AssemblyTitle
    -0.65
    POSITIVE LOGITS
     be
    0.97
    be
    0.58
    Be
    0.57
    findpost
    0.52
     Be
    0.51
     aient
    0.50
     mitte
    0.46
    ziu
    0.45
     soient
    0.44
    InjectAttribute
    0.44
    Activations Density 9.880%

    No Known Activations