© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12106
    Prev
    Next
    INDEX
    Explanations

    Constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_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
    \
    0.46
    ↵
    0.44
    NA
    0.40
    {
    0.38
    if
    0.38
    ation
    0.37
     for
    0.35
     la
    0.34
     forwarding
    0.34
    ık
    0.33
    POSITIVE LOGITS
     llrp
    0.46
    ۽
    0.46
     Fitbit
    0.43
    robespierre
    0.42
    marital
    0.42
    passport
    0.41
     ⇒
    0.41
     tenéis
    0.41
    txtbtn
    0.41
     Reverso
    0.40
    Activations Density 0.002%

    No Known Activations