© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10066
    Prev
    Next
    INDEX
    Explanations

    shortened words and actions

    oai_token-act-pair · gemini-2.0-flash

    say "d/u" 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     createSlice
    -0.55
    flü
    -0.51
     Clau
    -0.50
     sottile
    -0.50
     sobě
    -0.49
    AutoresizingMask
    -0.49
     تضيفلها
    -0.48
    assertRaises
    -0.47
     fût
    -0.46
     utafitiHapana
    -0.46
    POSITIVE LOGITS
     ur
    1.52
     Ur
    1.26
     da
    1.25
     d
    1.19
    Ur
    1.16
     dis
    1.11
     UR
    1.10
     de
    1.08
     dat
    1.00
     di
    0.91
    Activations Density 1.323%

    No Known Activations