© 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
    3. Gemma-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 341
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_12_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    0.15
     and
    0.15
     such
    0.14
     Such
    0.14
     oder
    0.13
     or
    0.13
     Gab
    0.13
     så
    0.13
     Så
    0.12
     (
    0.12
    POSITIVE LOGITS
     религиоз
    0.15
    currency
    0.14
    ⤒
    0.14
    ciphertext
    0.14
    Nonce
    0.13
    grayscale
    0.13
    isolate
    0.13
     Akshay
    0.13
    uyó
    0.13
    religious
    0.13
    Activations Density 1.706%

    No Known Activations