© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120293
    Prev
    Next
    INDEX
    Explanations

    numbers following prepositions

    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_27_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
     każdym
    0.41
     każde
    0.40
    大多數
    0.38
     большинства
    0.37
    許多
    0.37
    大多数
    0.36
     большинство
    0.36
    𝓼
    0.35
     wiele
    0.35
     każdy
    0.35
    POSITIVE LOGITS
     abord
    0.37
     Free
    0.33
     kif
    0.32
     sociable
    0.31
     Board
    0.31
     Overall
    0.31
     क्
    0.30
     Area
    0.30
     Jury
    0.30
     Gratis
    0.30
    Activations Density 0.001%

    No Known Activations