© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4954
    Prev
    Next
    INDEX
    Explanations

    applied or assigned

    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_39_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
     Boucher
    0.38
    важа
    0.36
    inker
    0.35
    誉
    0.35
    祗
    0.35
     mandarin
    0.35
    坎
    0.35
    Planck
    0.35
     Habits
    0.35
    祇
    0.35
    POSITIVE LOGITS
     applied
    1.43
    applied
    1.30
     aplicado
    1.17
    Applied
    1.15
     Applied
    1.11
     적용
    1.09
     aplicada
    1.05
     appliquée
    1.02
     applying
    0.99
     aplic
    0.98
    Activations Density 0.241%

    No Known Activations