© 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-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166593
    Prev
    Next
    INDEX
    Explanations

    It

    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_34_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
     Å
    0.36
    保有
    0.35
     spese
    0.34
    നാണ്
    0.34
    LocalizedString
    0.34
    jem
    0.33
     nj
    0.33
    它的
    0.33
     Momo
    0.33
    忐
    0.33
    POSITIVE LOGITS
     വെ
    0.35
     kuin
    0.33
     وبا
    0.32
     phú
    0.32
     vadati
    0.31
     early
    0.31
    Early
    0.31
     intramuscular
    0.31
     Contribution
    0.30
     ማስ
    0.30
    Activations Density 0.013%

    No Known Activations