© 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. 15650
    Prev
    Next
    INDEX
    Explanations

    a variety of characters, punctuation and numbers and some words related to business or demographics.

    oai_token-act-pair · gemini-2.0-flash

    say numbers

    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
     stället
    -1.03
     lèvres
    -0.99
     genoux
    -0.97
     supérieures
    -0.95
     degrés
    -0.93
     épaules
    -0.92
     cœurs
    -0.91
     gouttes
    -0.91
     jouets
    -0.91
     étrangère
    -0.90
    POSITIVE LOGITS
     Ballon
    0.31
     Vase
    0.28
     Cupcake
    0.27
     Nimbus
    0.27
     Galileo
    0.27
     whit
    0.26
     Nickel
    0.26
     Poseidon
    0.26
    3
    0.25
     Puff
    0.25
    Activations Density 15.052%

    No Known Activations