© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200405
    Prev
    Next
    INDEX
    Explanations

    ground beef

    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_12_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
     gaskets
    0.64
     tillage
    0.57
    rightsquigarrow
    0.57
     diligent
    0.55
     ricotta
    0.55
     legumes
    0.53
    r
    0.53
    ovaniyu
    0.52
     opportunities
    0.51
     patches
    0.49
    POSITIVE LOGITS
     Healing
    0.57
     Hid
    0.56
     નહીં
    0.56
     Gé
    0.54
    滏
    0.54
     logró
    0.53
     Adi
    0.53
    榱
    0.53
     Sid
    0.53
     leído
    0.53
    Activations Density 0.001%

    No Known Activations