© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205252
    Prev
    Next
    INDEX
    Explanations

    say or show

    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
     warm
    0.64
    Warm
    0.61
     Warm
    0.55
     ciep
    0.53
    warm
    0.47
    温
    0.47
     warmer
    0.47
    溫
    0.44
     warmly
    0.41
     plotted
    0.40
    POSITIVE LOGITS
     say
    0.75
     work
    0.67
     SAY
    0.65
     show
    0.64
     Say
    0.59
     offer
    0.56
    say
    0.56
     speak
    0.53
     care
    0.51
     lay
    0.51
    Activations Density 0.001%

    No Known Activations