© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166787
    Prev
    Next
    INDEX
    Explanations

    emotions

    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
    xcschemes
    0.38
     triste
    0.38
    Loving
    0.38
    欺
    0.37
    loving
    0.37
     loving
    0.36
    submenu
    0.36
    Concerning
    0.36
    模
    0.36
    0.35
    POSITIVE LOGITS
     anger
    0.51
     ang
    0.47
     general
    0.46
     break
    0.44
     sure
    0.43
     el
    0.42
     surety
    0.42
     constant
    0.41
     success
    0.41
     Ang
    0.40
    Activations Density 0.005%

    No Known Activations