© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32908
    Prev
    Next
    INDEX
    Explanations

    poetic, psychological, emotional depth

    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_40_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
     condemn
    0.50
     condemnation
    0.42
    ⸝
    0.41
    ങ്ങളുടെ
    0.41
    цыю
    0.40
    скую
    0.39
     condemns
    0.38
     ರಚ
    0.37
     criticise
    0.37
     condemning
    0.37
    POSITIVE LOGITS
    铨
    0.41
     திருப்ப
    0.41
    Charm
    0.40
     états
    0.39
    Hue
    0.39
    质
    0.38
    urno
    0.38
    计量
    0.38
    Heat
    0.38
    Amen
    0.38
    Activations Density 0.008%

    No Known Activations