© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20356
    Prev
    Next
    INDEX
    Explanations

    cre

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     simmering
    1.11
     fester
    1.09
     simmer
    0.79
    煮
    0.52
     boil
    0.47
     boiling
    0.47
     Boil
    0.44
    सेंट
    0.43
     incubation
    0.41
     boils
    0.41
    POSITIVE LOGITS
    Sim
    0.57
    sim
    0.55
     Sim
    0.52
     sim
    0.50
     simul
    0.44
    SIM
    0.41
     Simms
    0.41
     심
    0.40
     SIM
    0.40
     Simul
    0.39
    Activations Density 0.015%

    No Known Activations